Keynote MCP Server

by superdwayne

Overview Schema Related Servers Score Discussions

TypeScript

Local

Server Quality Checklist

Profile completionA complete profile improves this server's visibility in search results.

Latest release: v1.0.0
Disambiguation4/5
Most tools have distinct purposes, but some overlap exists between high-level design tools (design_deck, design_slide, design_from_template) and between get_full_presentation_content and get_presentation_info. Despite 70 tools, boundaries are mostly clear.
Naming Consistency4/5
Predominantly uses verb_noun pattern (add_slide, delete_image), but inconsistencies exist: 'list' vs 'get' for similar operations (list_slides vs get_slide_count), and 'change_slide_master' vs 'set_slide_background_color'. Minor mix of 'format_text' instead of 'set_text_formatting'.
Tool Count2/5
70 tools is excessive for an MCP server, far beyond the typical 10-20. While comprehensive, many tools (e.g., multiple design functions, separate list/get variants) could be consolidated. The high number risks overwhelming agents and increasing selection errors.
Completeness4/5
Covers nearly all aspects of Keynote automation: creation, editing, formatting, animations, transitions, exporting, slideshow control, and branding. Minor gaps exist (chart support is limited, no audio/video/hyperlink tools), but the surface is remarkably complete for a presentation tool.
Average 3.6/5 across 70 of 70 tools scored. Lowest: 2.4/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 0 commits in the last 12 weeks
- No stable releases found
- No critical vulnerability alerts
- No high-severity vulnerability alerts
- No code scanning findings
- CI is passing
Add a LICENSE file by following GitHub's guide. Once GitHub recognizes the license, the system will automatically detect it within a few hours.
If the license does not appear after some time, you can manually trigger a new scan using the MCP server admin interface.
MCP servers without a LICENSE cannot be installed.
This repository includes a README.md file.
No tool usage detected in the last 30 days. Usage tracking helps demonstrate server value.
Tip: use the "Try in Browser" feature on the server page to seed initial usage.
Add a glama.json file to provide metadata about your server.
If you are the author, simply .
If the server belongs to an organization, first add glama.json to the root of your repository:
```
{
  "$schema": "https://glama.ai/mcp/schemas/server.json",
  "maintainers": [
    "your-github-username"
  ]
}
```
Then . Browse examples.
Add related servers to improve discoverability.

How to sync the server with GitHub?

Servers are automatically synced at least once per day, but you can also sync manually at any time to instantly update the server profile.

To manually sync the server, click the "Sync Server" button in the MCP server admin interface.

How is the quality score calculated?

The overall quality score combines two components: Tool Definition Quality (70%) and Server Coherence (30%).

Tool Definition Quality measures how well each tool describes itself to AI agents. Every tool is scored 1–5 across six dimensions: Purpose Clarity (25%), Usage Guidelines (20%), Behavioral Transparency (20%), Parameter Semantics (15%), Conciseness & Structure (10%), and Contextual Completeness (10%). The server-level definition quality score is calculated as 60% mean TDQS + 40% minimum TDQS, so a single poorly described tool pulls the score down.

Server Coherence evaluates how well the tools work together as a set, scoring four dimensions equally: Disambiguation (can agents tell tools apart?), Naming Consistency, Tool Count Appropriateness, and Completeness (are there gaps in the tool surface?).

Tiers are derived from the overall score: A (≥3.5), B (≥3.0), C (≥2.0), D (≥1.0), F (<1.0). B and above is considered passing.

Tool Scores

Behavior1/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description should fully disclose behavior. It lacks any mention of side effects, error conditions, or return value. Minimal behavioral information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One sentence with 15 words, front-loaded with the action. Efficient, but could be slightly more informative without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness1/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 7 parameters, no output schema, and no annotations, the description is severely incomplete. It does not address positioning defaults, slide existence, or interaction with other elements.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already describes parameters. The description merely repeats 'rows and columns' without adding new context. No value added.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Adds') and resource ('table to a slide') and mentions key parameters (rows and columns). However, it does not differentiate from sibling tools like add_shape or add_chart.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., add_shape for non-table elements). No context about prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description only says 'adds', which implies a write operation. It does not disclose whether adding an animation replaces or stacks with existing animations, idempotency, or any side effects. Minimal behavioral context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences with front-loaded action and clear explanation of the two build types. It is concise with no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so return value information is absent. For a mutation tool, behavioral details like default duration handling, error conditions, and interaction with existing animations are missing, making it incomplete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already describes all parameters. The description adds no extra meaning beyond the schema, meeting the baseline but not exceeding it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool adds an animation to an item, and it distinguishes between build-in and build-out. It implicitly differentiates from sibling tools like remove_build_animation, but does not explicitly contrast with alternatives.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives or when not to use it. There is no mention of prerequisites, conflicts with existing animations, or related tools like list_build_animations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states that the tool 'removes' a text item but does not mention any side effects, irreversibility, permissions required, or the state of the slide after deletion. This lack of detail limits transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single succinct sentence with no wasted words. However, it is arguably under-specified for a tool with two parameters and no annotations. Conciseness is achieved at the expense of completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a deletion tool with two simple parameters and no output schema, the description lacks important context such as whether the operation is reversible, how it interacts with other elements (e.g., animations), or the impact on the slide structure. It does not fully equip an agent to understand the tool's effects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the description adds minimal new meaning beyond the parameter names and types. It reiterates 'text item' and 'slide' but does not explain concepts like how to identify valid indices or constraints on the operation, thus adding the baseline value for high coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool removes a text item from a slide, with a specific verb and resource. However, it does not differentiate from sibling deletion tools like delete_shape or delete_image, which perform analogous actions on different resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives such as update_text_item (which modifies rather than removes) or other deletion tools. No contextual cues are given for appropriate usage scenarios.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose potential side effects like overwriting existing content or formatting changes. It only states the basic operation without behavioral details.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 11 words, front-loading the action without any waste. It is appropriately concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having 5 required parameters, no output schema, and no annotations, the description is minimal. It lacks information on return values, error handling, and prerequisites, making it incomplete for a modification tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters. The description adds no extra meaning beyond what the schema provides, thus meets the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (sets) and resource (value of a specific cell in a table on a slide). It differentiates from sibling tools like 'set_table_data' implicitly by focusing on a single cell, but does not explicitly contrast them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as 'set_table_data'. No prerequisites or error conditions (e.g., table must exist) are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It does not mention whether removal is permanent, undoable, or requires saving. No information about side effects or authorization needs.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no unnecessary words. It is front-loaded and concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple two-parameter tool, the description is adequate but lacks context about return values (no output schema) and whether any follow-up steps are needed. Additional behavioral context would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the schema already describes both parameters as 1-based indices. The description adds no additional meaning beyond what the schema provides, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (removes) and the resource (image from a slide), and the name alone distinguishes it from sibling tools like delete_shape or replace_image. However, it does not explicitly differentiate from other deletion tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as replace_image or delete_shape. There is no mention of prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It fails to disclose whether the tool creates new slides or modifies existing ones, or any side effects like overwriting content. Only hints at automatic layout variety and branding.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence of 9 words, very concise. It captures the essence without fluff, but could be slightly expanded to include when to use or important notes.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Missing output schema, so description should compensate by hinting at return value or outcome. It does not. Also doesn't explain how 'consistent branding' is achieved or how many slides can be designed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema fully documents parameters. The description adds no extra meaning beyond the schema, meeting the baseline. No credit given for repeating parameter info.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the tool designs multiple slides at once, differentiating it from sibling 'design_slide' which handles single slides. It also specifies unique features: automatic layout variety and consistent branding.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives like 'design_slide' or 'design_from_template'. The description implies batch use but does not state prerequisites or contraindications.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits but only states it 'designs' a slide. It does not clarify if existing content is overwritten or merged, what permissions are needed, or any side effects, leaving significant ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence (15 words) that front-loads the core purpose. It could be more structured with separate aspects, but it is efficient and without waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has 14 parameters and no output schema or annotations, the one-sentence description is insufficient. It fails to explain the automatic layout algorithm, the effect of multiple content fields, or the return value, leaving agents underinformed for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters. The description adds marginal context like 'automatic layout' and 'optional brand settings', but does not deepen meaning beyond the schema, earning a baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool designs a complete slide with automatic layout, typography, and color, distinguishing it from sibling tools like set_slide_title or design_deck by focusing on a single slide's comprehensive design.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like design_deck (for entire deck) or design_from_template. The description does not include any when/when-not or prerequisite context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It only states the action 'sets' but does not disclose side effects, required permissions, or error handling (e.g., if slide doesn't exist).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no fluff, front-loaded with verb and object. Could be slightly more informative without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema, no annotations, and description is minimal. Does not address return value, error conditions, or potential effects on presentation state.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline score applies. Description does not add extra meaning beyond what schema already provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'sets' and resource 'presenter notes for a specific slide'. It distinguishes from sibling tools like get_presenter_notes and get_all_presenter_notes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, no prerequisites or exclusions mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided. Description lacks details on whether it replaces existing body text or appends, any prerequisites (e.g., slide existence), or effects on existing content.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single concise sentence is efficient, but could be slightly more structured (e.g., specifying scope of body text).
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Simple tool with 2 params, but no output schema and minimal description. Lacks behavioral details (e.g., replacement behavior, error conditions). Could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema describes both parameters fully. Description adds no extra meaning beyond schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the verb 'Sets' and resource 'body text of a slide', distinguishing it from siblings like 'set_slide_title' and 'update_text_item'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool vs alternatives such as 'set_text' or 'format_text'. No exclusions or context for appropriate use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description must convey behavioral traits. It only states it adds an image, but does not discuss file accessibility, error handling, or effects of invalid file paths.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence that is direct and front-loaded. No extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and 7 parameters, the description lacks essential context: error conditions, image format support, intrinsic sizing behavior, and the need for the slide to exist.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the description does not need to add much. However, it does not elaborate beyond the schema, e.g., defaults for x/y or the role parameter's impact. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (adds), resource (image file to a slide), and key attributes (position, optional width/height). It distinguishes from siblings like delete_image or replace_image by specifying the insertion operation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives such as replace_image or set_image_position. No context about prerequisites or scenarios where this tool is preferred.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral disclosure. It only states the basic action without revealing side effects, prerequisites (e.g., must have an open presentation), or return behavior (e.g., does it return the new slide ID?).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise with two short sentences. It is front-loaded with the core action. However, it lacks structured formatting (e.g., bullet points) that could improve readability.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description provides minimal context. It does not explain what 'frontmost presentation' means, failure scenarios, or success indicators. It is adequate but incomplete for a tool with two optional parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with both parameters already described in detail. The description adds no new information beyond 'optionally specify position and master slide name', which is already evident from the schema. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb (adds), resource (slide), and target (frontmost presentation). It also mentions optional parameters, making its purpose distinct from sibling tools like duplicate_slide or move_slide.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide when to use this tool versus alternatives. It lacks exclusions or references to related sibling tools, leaving the agent to infer usage context from tool names alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden but only states the core action. It does not disclose potential side effects (e.g., discarding changes if saving=false), error conditions (e.g., no presentation open), or confirmation behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is one sentence long, efficient, and front-loaded with the action. It is appropriately sized for a simple tool, but lacks any structural elements like bullet points.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and single optional parameter, the description is adequate but incomplete. It does not mention what happens if no presentation is open or the implications of the saving parameter on user experience.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema fully describes the single parameter with 100% coverage. The description adds no additional meaning beyond 'closes', so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Closes') and resource ('frontmost Keynote presentation'), clearly distinguishing it from sibling tools like 'open_presentation' or 'save_presentation'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not specify when or why to use this tool versus alternatives, nor does it mention prerequisites or typical workflows. It lacks explicit guidance on usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits but only states the basic action. It does not explain outcomes like whether the table data is also removed, error conditions, or side effects on other slide elements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise (5 words), front-loaded, and contains no unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a mutation tool with no annotations and no output schema, the description is too minimal. It lacks prerequisites, return values, and edge cases, making it incomplete for safe agent usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both parameters described ('1-based slide index', '1-based table index'). The description adds no additional meaning beyond the schema, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('removes') and the resource ('a table from a slide'), distinguishing it from sibling delete tools for images, shapes, slides, and text items.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus other table-related tools (e.g., set_table_cell, set_table_data) or alternatives for modifying tables.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavioral traits. It only states 'exports' but doesn't disclose whether the operation is read-only, whether it overwrites existing files, permission requirements, or side effects. This leaves significant ambiguity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that efficiently conveys the core action. It lacks structure but contains no fluff or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool, the description adequately states the purpose. However, it omits details about behavior (overwrite, error handling) and assumptions (frontmost presentation). While minimal, it covers the essential goal.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides a detailed description of the filePath parameter with an example path. The tool description adds no additional context about the parameter, so it meets the baseline for high schema coverage but doesn't add extra value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Exports'), the resource ('frontmost Keynote presentation'), and the output format ('PDF file'). It distinguishes from sibling tools like export_to_pptx (different format) and export_to_images (multiple outputs).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternative export tools (e.g., export_to_pptx, export_to_images). It doesn't mention prerequisites like having a presentation open, nor when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries full burden for behavioral disclosure. It only states 'formats' without explaining whether it overwrites or merges formatting, if existing formatting is cleared, or if it requires the text item to already exist. No side effects or requirements are mentioned.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 12 words, efficiently conveying the tool's purpose without redundancy. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With 8 parameters, no output schema, and no annotations, the description is too brief. It does not explain parameter interactions, default behavior for omitted parameters, or the need for slideIndex and itemIndex to locate the text item. The description is incomplete for a tool of this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with detailed parameter descriptions, so the description adds no extra meaning beyond listing categories. Baseline 3 applies as the schema already handles semantics.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool formats a text item with specific formatting options (font, size, color, bold, italic, alignment), distinguishing it from sibling tools like update_text_item which may have broader scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as update_text_item or add_text_item. The description does not specify prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description should disclose mutation behavior. It does not state whether the tool replaces all table data, merges, or requires the table to exist. No mention of side effects, permissions, or limits.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with the core purpose. No redundant information; each sentence contributes meaning.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema and no annotations, the description is insufficient. It does not explain the effect on existing data, prerequisites, or return value, leaving significant gaps for a mutation tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the description does not add meaning beyond what the schema's descriptions already provide. It repeats the concept of a 2D array but adds no new semantic detail.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool bulk-sets table data using a 2D array of strings, with each inner array as a row. This effectively distinguishes it from siblings like set_table_cell and get_table_data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives (e.g., set_table_cell). The word 'Bulk-sets' implies it's for updating multiple cells at once, but no direct comparison or exclusions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosing behavior. It only states that text content is updated, without mentioning side effects (e.g., does it reset formatting?), error conditions, or idempotency. This is insufficient for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the purpose. It is efficient and contains no fluff, though it could benefit from slight expansion to cover usage context.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with only three parameters, and the schema covers them well. The description explains the core action but does not provide workflow context (e.g., when to use after adding a text item) or mention index conventions already in the schema. It is minimally adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, and the input schema already describes each parameter (slideIndex, itemIndex, text) with clear descriptions. The tool description adds no additional semantic meaning beyond what the schema provides, so the baseline score of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Updates' and the specific resource 'text content of an existing text item on a slide'. It distinguishes itself from sibling tools like add_text_item, delete_text_item, and format_text, which handle different operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., the item must exist) or scenarios where another tool would be preferred. The description implies usage for updating text but lacks comparative context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavior. It only states it creates a presentation and optionally accepts a theme. It omits critical details like whether the presentation is saved, how to reference it later, or any side effects. The description is too sparse for a creation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no wasted words. It efficiently conveys the core action and optional parameter. Could be slightly improved by front-loading the result, but overall concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is very basic. It doesn't explain what 'blank' means, what happens to existing presentations, or how to access the new presentation. Given the lack of output schema and the complexity of Keynote workflows, this is incomplete. A user would need to infer behavior from sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% coverage with a clear description for themeName. The description adds 'Optionally specify a theme name' which matches the schema. Schema handles semantics well, so description provides minimal additional value. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it creates a new blank Keynote presentation. This is specific and distinguishes from sibling tools like open_presentation or apply_theme.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when a new presentation is needed but provides no guidance on when not to use it or how it compares to alternatives like design_from_template or apply_theme. No explicit context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, and the description only says 'removes' without elaborating on permanence, side effects, or prerequisites. For a destruction operation, the agent needs more behavioral clarity.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence, which is efficient. However, it lacks any structure (e.g., bullet points) that could improve readability, but it is not overly verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and the fact that the schema covers parameters, the description is mostly complete. It could mention how indices relate to list_shapes, but it is adequate for a basic delete operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already describes both parameters. The description adds no additional meaning beyond what the schema provides, meeting baseline expectations.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Removes' and the resource 'shape from a slide', which is specific and distinguishes it from sibling tools like delete_image or delete_slide that target different resources.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like update_shape (which could remove shapes by changing properties) or other deletion tools. The description lacks context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry full behavioral disclosure. It fails to mention critical details such as file naming conventions, overwrite behavior, error conditions (e.g., directory does not exist, no open presentation), or whether the operation is blocking. These omissions reduce transparency significantly.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The single-sentence description is concise and front-loaded with the key action. It could be improved by adding a bit more structure (e.g., noting file naming conventions) without becoming verbose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no output schema or annotations, the description should provide more context. It lacks details about return values, error handling, file naming, and dependencies (e.g., presentation must be open). These gaps make it incomplete for an agent to use confidently.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides full coverage (100%) with descriptions for both parameters. The description adds no additional meaning or context beyond the schema, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool exports all slides of the frontmost presentation as individual image files to a directory. It uses a specific verb (exports) and resource (all slides), and implicitly distinguishes itself from siblings like export_slide_to_image (single slide) and export_to_pdf (PDF format).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage: when you need images of all slides. However, it does not explicitly mention when to use this tool versus alternatives (e.g., export_slide_to_image for single slides) or provide any exclusions, prerequisites, or context on when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description does not disclose any behavioral traits beyond the basic action of moving. It does not mention side effects, such as whether the slide is selected after moving, if the operation is reversible, or any permissions required. With no annotations present, the description carries the full burden but fails to provide sufficient detail.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that immediately conveys the core action. It is front-loaded and free of redundancy, though it could be slightly expanded to include more detail without becoming wordy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (2 required integer parameters, no output schema, no nested objects), the description provides a sufficiently complete overview of the operation. However, it lacks information about edge cases, error handling, or the effect on the presentation state, which would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both parameters having clear descriptions (1-based indices). The description adds no further meaning beyond restating 'from one position to another'. Baseline of 3 is appropriate as the schema already documents the parameters adequately.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'moves' and the resource 'slide', specifying a change in position within the frontmost presentation. It is distinct from sibling tools, which include actions like add, delete, duplicate, or navigate slides, but none other that reorder slides.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, nor are there any preconditions, error conditions, or context for usage. The description lacks explicit when-to-use, when-not-to-use, or alternative tool mentions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as whether the operation is idempotent, whether it overwrites existing title text, or what happens if the slide lacks a title placeholder.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, short sentence with no unnecessary words. It is front-loaded and communicates the essential purpose efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple setter tool with 2 parameters and no output schema, the description is minimally adequate. However, it could mention the return value or the effect on existing title text to be fully complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents both parameters. The description adds no extra meaning beyond what is in the schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action (Sets) and the resource (title text of a slide). The verb+resource pattern is specific and distinguishes it from sibling tools like set_slide_body or set_slide_background_color.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives, nor any conditions for use. The description simply states what it does without providing context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It only states what the tool does without disclosing side effects, error behavior, idempotency, permissions, or return values. Minimal behavioral transparency beyond the core action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence (15 words) with no redundancy. It efficiently conveys the essential action and key parameters without extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity (8 parameters, no output schema), the description lacks critical context. It omits details like coordinate system, 1-based slide index, the 'role' parameter, and expected return value. Incomplete for an agent to fully understand usage implications.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description adds 'optional fill colour' which echoes the fillColor parameter description. It does not add new semantic meaning beyond summarizing the schema's already documented parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'adds' and identifies the resource 'shape to a slide'. It mentions key parameters (type, position, size, optional fill colour), distinguishing it from sibling tools like update_shape and delete_shape.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when adding a shape to a slide but provides no explicit guidance on when to use this tool versus alternatives (e.g., add_image, add_text_item) or prerequisites (e.g., slide existence). No when-not-to-use or context-specific advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses output fields (content, position, size) but lacks details on read-only nature, error handling for invalid slide indices, or any side effects. Sufficient for a simple list operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no unnecessary words. Every part (verb, resource, scope, output fields) earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-parameter list tool with no output schema, the description covers key output fields. Could mention ordering or performance, but overall complete enough given simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (slideIndex described with integer, minimum, 1-based). The tool description adds no further meaning beyond schema, hitting the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose4/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Lists') and specifies the resource ('all text items') and scope ('on a slide'), clarifying it retrieves only text items. It distinguishes from siblings like 'list_shapes' by focusing on text items, though slight ambiguity remains if shapes can contain text.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., 'list_shapes' or 'get_slide_content'). No prerequisites or context for its appropriate use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not elaborate on behavioral aspects such as whether the operation is reversible, file format constraints, or what happens to the old image. For a mutation tool, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, directly communicates the purpose with no extraneous information. Efficiently front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the absence of annotations and output schema, the description is too minimal. It omits return behavior, side effects, and prerequisites, leaving the agent underinformed for a tool with three required parameters.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (all three parameters have descriptions). The tool description does not add additional context beyond what the schema already provides, so baseline score is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Replaces an existing image on a slide with a new image file'), specifying the verb 'replaces', the resource 'image on a slide', and the action of swapping with a new file. This distinguishes it from siblings like add_image (adds new) and delete_image (removes).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives. The description merely states what it does; it does not specify prerequisites, scenarios, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden for behavioral disclosure. It states it sets a 'solid' color but does not mention that it overwrites existing backgrounds, requires the slide to exist, or any limitations. The hex pattern is already in the schema, so the description adds minimal value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no unnecessary words. Information is front-loaded and easy to parse.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple mutation tool with no output schema, the description covers the purpose and parameter usage adequately. It could be improved by noting that it replaces any existing background, but overall it is reasonably complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the baseline is 3. The description provides an example hex value, but the schema already contains a description with examples. The description adds no additional semantic meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Sets'), the resource ('solid background color on a slide'), and distinguishes from sibling tool set_slide_background_image by specifying 'solid'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like set_slide_background_image. The agent receives no context for prioritization or exclusion.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It discloses that the tool modifies attributes, but does not mention whether it overwrites existing values, side effects, or required permissions. The description is adequate but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is concise and front-loaded with the purpose. No unnecessary words or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness2/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema is provided, and the description does not mention return values or confirmation. With 9 parameters and no indication of what the tool returns after modification, the description is incomplete for an agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the description adds little beyond listing the attributes. It does not provide additional meaning or constraints beyond what is in the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Modifies' and the resource 'a shape', and lists the specific attributes that can be changed (position, size, fill colour, border colour, border width). This distinguishes it from sibling tools like delete_shape or add_shape.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like update_text_item or set_image_position. There is no mention of prerequisites, context, or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided. The description does not disclose behavioral traits like whether it overwrites existing presentations, prerequisites (e.g., presentation open), error behavior, or return value. For a tool with no annotations, the description carries the full burden and is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single, clear sentence with no wasted words. Essential information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given 5 parameters, no output schema, and no annotations, the description is adequate but has gaps. It lacks return value, prerequisites, and differentiation from related tools like design_deck.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents each parameter. The description adds no additional meaning beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Creates' and the resource 'full presentation from a template', with the method 'using the template's layout sequence with provided content'. It distinguishes this from siblings like create_presentation (no template) and design_slide (single slide).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The purpose implies use for creating presentations from templates, but there are no explicit guidelines on when to use or avoid this tool. It does not reference alternatives such as create_presentation or design_deck.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden to disclose behavioral traits, but it omits key details: where the duplicate is inserted (e.g., after the original), whether it copies all content, or any side effects like changing the active slide. This lack of transparency may lead to incorrect agent behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence conveys the essential action, resource, and indexing. Every word is necessary; no fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the single parameter and no output schema, the description is minimally adequate for a simple duplication action. However, it lacks completeness regarding the insertion behavior and overall effect, which could be inferred but not from the description alone.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and already documents slideIndex as 1-based integer. The description repeats this information without adding new semantic context like formatting constraints or valid ranges, so it meets the baseline but adds no extra value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Duplicates') and resource ('slide'), identifies the indexing scheme ('1-based index') and context ('frontmost presentation'), clearly distinguishing it from sibling tools like delete_slide or move_slide.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when a copy of a slide is needed, but provides no explicit guidance on when to use this tool vs alternatives (e.g., add_slide, then copy content), nor any prerequisites or limitations.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavior. It does not mention side effects, read-only nature, performance implications (potentially large payload), or return structure. Only lists contained elements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence with clear structure, no redundancy. All content types listed efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Adequate for a single-parameter tool, but missing description of return format or volume. Sufficient for basic understanding but could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema already describes slideIndex as 1-based integer. Description adds minimal value by listing content types, but does not provide additional parameter details beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states it returns all content on a specific slide and lists specific content types (title, body, text items, images, shapes, tables, presenter notes). Distinguishes from siblings like get_full_presentation_content (all slides) and get_slide_count (count only).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use vs alternatives. While the purpose is clear, there is no mention of when not to use it (e.g., for bulk retrieval) or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It only states what it gets, but does not mention what happens if no transition is set, whether the operation is read-only, or any potential side effects. For a read operation, more clarity on default values or null returns would be beneficial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that directly states the tool's functionality. No wasted words or unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has one parameter and no output schema, the description provides a basic understanding but lacks detail on the return format (e.g., object structure) and edge cases. For a simple getter, it is marginally adequate but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (slideIndex with min and description). The description adds no additional meaning beyond what the schema already provides. Baseline score of 3 applies as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Gets'), the resource ('current transition effect, duration, and delay'), and the target ('for a slide'). It distinguishes from sibling tools like 'set_slide_transition' and 'list_transition_types' by focusing on retrieval of specific properties.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for reading existing transition settings, but it does not explicitly state when to use this tool versus alternatives like 'set_slide_transition' or provide any prerequisites or context (e.g., slide must have a transition). No when-not or alternative guidance is given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden for behavioral disclosure. It does not state that the tool is read-only, safe, or lacks side effects. It also fails to mention any rate limits or pagination behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence with no fluff. Every word contributes to explaining what the tool does and what it returns.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple read-only list tool with one optional parameter and no output schema, the description covers the essentials: what is listed and the details returned. It is nearly complete, though it could mention that the output is a list of layout objects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters2/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes the 'category' parameter with an enum and description. The tool description adds no additional meaning or context about the parameter beyond what the schema provides.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all available slide layouts and specifies the included details: descriptions, categories, and element details. It distinguishes from siblings like get_slide_layout_names which only returns names.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for browsing layouts but does not explicitly say when to use it versus alternatives like get_slide_layout_names. No exclusions or when-not-to-use guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It only states the action without disclosing behavioral traits such as error handling (e.g., if no animation exists), reversibility, or permission requirements. This is insufficient for an agent to understand side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence that conveys the essential purpose without any wasted words. It earns its place by being maximally concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has no output schema and no annotations, but the description covers the basic action. However, it omits return behavior or success indicators. Given the simplicity of the tool (3 required params), this is minimally viable but not complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with each parameter clearly described in the input schema. The description adds no additional meaning beyond the schema, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('removes') and clearly identifies the resource ('build-in or build-out animation from an item on a slide'). It immediately distinguishes from sibling tools like 'add_build_animation' and 'list_build_animations'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage (when you want to remove an animation) but provides no explicit guidance on when not to use it, prerequisites (e.g., animation must exist), or alternatives. It is adequate for a straightforward tool but lacks depth.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description should disclose behavioral traits (e.g., whether it modifies in place, permissions needed). The description only states the action without any side effects or constraints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no fluff, directly states purpose. Efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is straightforward, but no output schema is provided and the description does not mention return values or potential side effects. For a mutation tool, this is minimally adequate but could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so the schema already documents all parameters. The description does not add additional meaning beyond the schema, which is adequate but not enhanced.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action (repositions/resizes) and the target (existing image on a slide). It distinguishes from sibling tools like replace_image and delete_image.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives, but the name and description make the usage context clear. A better description would specify that it is for adjusting position/size without replacing the image.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the file accessibility constraint but lacks details on error behavior (e.g., missing file), image scaling, or whether existing background is replaced. For a tool with no annotations, this is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no unnecessary words. Every sentence adds value: the first states purpose, the second adds a critical prerequisite.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with two params and no output schema. The description covers the core action and a key constraint, but lacks behavioral context (e.g., error handling, side effects). It is minimally adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with descriptions already explaining filePath and slideIndex. The description adds only the local filesystem requirement, which is a minor addition. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('sets an image file as the background of a slide') and effectively distinguishes it from sibling tools like set_slide_background_color. The resource and action are unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions a prerequisite (file must be locally accessible) but does not explicitly guide when to use this tool over alternatives (e.g., set_slide_background_color). No exclusions or when-not conditions are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must fully disclose behavioral traits. It only states the action and optional starting slide, but does not mention side effects (e.g., whether it changes presentation state), failure conditions (e.g., no presentation open), or whether it is idempotent. This lack of detail leaves the agent in the dark about critical behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise: a single sentence with no unnecessary words. It front-loads the key action and includes the optional parameter. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity (one optional parameter, no output schema), the description is minimally adequate but has gaps. It does not mention that the presentation must be frontmost or that starting a slideshow might interrupt an existing one. For a simple action, it is functional but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with the 'fromSlide' parameter well-described in the schema (type, description, exclusive minimum). The description merely echoes 'Optionally start from a specific slide', adding no new semantic value beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it starts the slideshow of the frontmost Keynote presentation, optionally from a specific slide. The verb 'starts' and resource 'slideshow of frontmost Keynote presentation' are specific and well-distinguished from siblings like stop_slideshow, next_slide, etc.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when one wants to start a slideshow, but does not provide explicit guidance on when to use versus alternatives (e.g., go_to_slide, next_slide). There is no mention of when not to use or prerequisites, such as requiring a presentation to be open.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description only states the removal action without disclosing behavioral traits such as authentication needs, reversibility, or side effects. For a destructive operation, more transparency is warranted.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no fluff. All key information is front-loaded: verb, resource, index, and scope. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter delete tool with no output schema or annotations, the description is adequate. It explains what index means and what presentation it targets. Missing details like error handling or bounds behavior are acceptable at this complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema has one parameter with description covering 100%. Description adds 'frontmost presentation' context, which provides marginal additional value beyond the schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly specifies the verb (removes), resource (slide), and method (1-based index, frontmost presentation). It effectively distinguishes from sibling tools like delete_shape and delete_image.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description implies when to use this tool (to remove a slide) but provides no explicit guidance on when not to use it or alternatives. No exclusion criteria or context for switching to other tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It indicates a read operation ('gets') with no mention of side effects, but fails to disclose required permissions, idempotency, or whether the returned structure includes all details. Lacks explicit safety guarantees beyond the verb choice.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-formed sentence that front-loads the key action and resource. It is concise but could benefit from separate sentences for the return value details. No wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description should clarify the return structure. It mentions 'slide-by-slide layout and content hints' but does not specify the format (e.g., list of slides with fields). The tool complexity is moderate, and more detail would help agents anticipate output.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single parameter. The schema already provides examples of valid template names. The description adds no additional meaning beyond what the schema offers, so a baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool gets the full structure of a specific presentation template with slide-by-slide layout and content hints. It specifies the resource ('presentation template') and the outcome ('full structure'), distinguishing it from sibling tools like list_templates and get_full_presentation_content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not explicitly state when to use this tool vs alternatives. While the purpose is clear, there is no guidance on when to choose get_template over list_templates or other exploration tools. Usage context is implied but not articulated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description implies a read-only operation but does not explicitly state non-destructiveness or any behavioral traits. With no annotations, more disclosure could be beneficial, but the description is minimally adequate for a simple list tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence that efficiently conveys the tool's purpose without extraneous information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one parameter, no output schema), the description adequately covers the return info (position, size, file name). However, it could specify the return format (e.g., array) for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema covers 100% of the parameter description (slideIndex as 1-based integer). The description adds no extra meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Lists', the resource 'images on a slide', and the specific information returned (position, size, file name). It distinguishes itself from sibling tools like list_shapes or list_text_items by focusing solely on images.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives (e.g., get_slide_content for full slide details). It lacks prerequisites or context for proper invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Only says 'opens', no details on what happens (e.g., opening in new window, error on missing file, side effects). Without annotations, description is insufficient.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no unnecessary words. Front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Simple tool (1 param, no output schema). Description provides essential purpose; could add constraints like file existence, but adequate for low complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters. Description adds no value beyond restating 'file path'. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states verb 'opens', resource 'Keynote presentation', and constraint '.key file by file path'. Distinct from sibling tools like create_presentation and close_presentation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit when-to-use or when-not-to-use guidance. Implied use for opening existing .key files, but no exclusion of alternatives or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden. It discloses creation with position/size but fails to mention constraints (e.g., slide index validity), side effects, or error scenarios. Minimal behavioral context beyond the basic action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence of 12 words, front-loading the key action with no extraneous information. Efficient and clear.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Description is minimal for a tool with 8 parameters (including optional role and autoPosition) and no output schema. It does not explain what happens after addition, return values, or how optional parameters affect behavior, leaving gaps for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the description adds little beyond stating 'position and size'. All 8 parameters are documented in the schema, making the description's contribution marginal according to the baseline rule.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb 'adds', resource 'text box', and specifics 'to a slide at a specified position and size', effectively distinguishing it from sibling tools that add other elements (add_image, add_shape, etc.).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide guidance on when to use this tool versus alternatives (e.g., update_text_item for editing). No exclusions or context are given, relying on the agent to infer from the name alone.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as side effects (e.g., content reshaping), permissions required, or reversibility, which is critical for a mutation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences, front-loaded with the purpose. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description is functional but lacks detail about error scenarios (e.g., invalid master name) and behavioral effects on slide content.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema provides 100% coverage with descriptions and examples. The description adds extra context by requiring that masterName must match available masters, which is not in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Changes' and the resource 'master slide (layout) of a slide', distinguishing it from sibling tools like get_slide_layout_names or apply_theme.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description advises that the master name must match available masters but does not explicitly state when to use this tool vs alternatives like get_slide_layout_names, nor does it provide caution about when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must convey behavioral traits. It indicates the tool operates on the frontmost presentation, but does not disclose error behavior (e.g., if no presentation is open), overwrite behavior for existing filePath, or any side effects. The description provides minimal but sufficient transparency for a straightforward export action.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 11 words with no redundant information. It is concise and directly states the tool's purpose without unnecessary elaboration.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (one required parameter, no output schema, no annotations), the description is minimally complete. It covers the basic function but lacks contextual details about error handling, requirements, or comparison with similar tools. For a one-parameter export, this may be acceptable, but additional context would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the schema already describes filePath as 'Absolute POSIX path for the output .pptx file'. The description does not add any additional meaning beyond what the schema provides, so it meets the baseline expectation without exceeding it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'exports', the resource 'frontmost Keynote presentation', and the output format 'Microsoft PowerPoint (.pptx) file'. It effectively distinguishes this tool from siblings like export_to_pdf or export_slide_to_image by specifying the file format.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when the user wants a .pptx file from the frontmost presentation, but it does not provide explicit guidance on when to use this tool vs alternatives (e.g., export_to_pdf), nor does it state prerequisites (e.g., must have an open presentation). The context is clear but lacks exclusionary or comparative notes.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. It indicates a read operation ('gets') but does not disclose possible return values (text, null, side effects) or behavior for invalid indices, which is minimal but not misleading.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence of 9 words, front-loaded with key action and object, no wasted content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Description covers basic purpose but lacks details on return format, error behavior for missing notes or invalid indices, and prerequisites. Given no output schema, more completeness would be helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and already describes the slideIndex as '1-based slide index'. The description adds no additional meaning beyond what the schema provides, so baseline score applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it gets presenter notes for a specific slide, with a specific verb and resource, distinguishing it from sibling tools like get_all_presenter_notes and set_presenter_notes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage context is implied (to retrieve notes for one slide), but no explicit guidance on when to use this vs alternatives like get_all_presenter_notes or set_presenter_notes, nor any conditions for use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the basic action (jumping to a slide) and the requirement of an active slideshow, but it does not mention error handling (e.g., out-of-range index), side effects, or return behavior. This is adequate but minimal for a simple navigation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, front-loaded sentence of 9 words with no unnecessary information. Every word contributes to the purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter and no output schema, the description provides the core functionality. However, it lacks details on return values or error conditions, which would help the agent handle edge cases. It is adequate but not thorough.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides a full description for the single parameter (slideIndex: 1-based integer). The description adds no additional meaning beyond déjà-vu. Given 100% schema coverage, baseline score 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'jumps' and the resource 'specific slide' in the context of an 'active Keynote slideshow'. This distinguishes it from sibling tools like next_slide and previous_slide, which navigate sequentially, and start_slideshow, which initiates the show.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is for jumping to a specific slide, but it does not explicitly state when to use it versus alternatives like next_slide or previous_slide. No exclusions or prerequisites beyond 'active slideshow' are provided, limiting guidance for the agent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must fully disclose behavior. It mentions the default to the frontmost presentation and lists returned fields, but does not clarify error handling (e.g., if no presentation is open) or side effects. For a read-only info tool, this is acceptable but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, each crucial: first enumerates the output, second explains default behavior. No fluff or redundancy. Information is front-loaded and efficiently presented.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (one optional param, no output schema, read-only), the description is largely complete. It could mention that the name must match exactly or that the file is opened automatically, but these are minor omissions. Overall, it provides sufficient context for usage.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (the parameter 'name' is described as 'Name of the presentation. If omitted, uses the frontmost document.'). The tool description repeats the default behavior but adds no new meaning beyond the schema. Baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's action: 'Returns slide count, theme name, dimensions, and file path for a presentation.' It specifies the resource (presentation) and the type of information retrieved. This distinguishes it from sibling tools that get specific subsets (e.g., get_slide_count, get_presenter_notes).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for obtaining multiple presentation properties but does not explicitly state when to use this tool versus alternatives like get_full_presentation_content or get_slide_count. No exclusions or comparisons are provided, leaving room for confusion among many similar get* tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for behavioral context. It only states what the tool does without revealing side effects, errors, or prerequisites (e.g., whether an open presentation is required, or what happens if no theme exists).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single clear sentence with no superfluous words. It is front-loaded with the action and resource.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite the absence of annotations and output schema, the description adequately covers the tool's purpose and output for its simplicity. It could specify that it returns an array of strings, but the context is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and the schema coverage is 100% (empty schema). The description adds meaning by clarifying that the tool returns 'master slide (layout) names' rather than just listing arbitrary elements.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'lists', the resource 'master slide (layout) names', and the context 'current theme of the frontmost presentation'. It is specific and distinguishes itself from sibling tools like 'list_layouts'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving layout names but provides no explicit guidance on when to use this tool versus alternatives, nor any when-not-to-use conditions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It states it gets a name but doesn't disclose potential errors, authorization needs, or that it's a safe read operation. Does not contradict annotations (none exist).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no fluff, front-loaded with key action and resource. Every word is necessary and informative.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter getter with no output schema, the description is fairly complete. It specifies what is returned (name) and the input. Minor gap: doesn't explain format of the name.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema covers 100% of parameters with clear description ('1-based slide index'). Description adds no extra meaning beyond schema. Baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states action ('Gets') and resource ('master slide name') for a given slide. Differentiates from siblings like 'change_slide_master' (modification) and 'get_slide_layout_names' (list all).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool vs alternatives. Usage is implied by the name and description, but lacks context for when a user might need this or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden. It discloses the return format (2D array of strings), which is helpful, but does not mention error handling, edge cases (e.g., empty table), or any side effects. For a simple read operation, this is adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no extraneous words. It is front-loaded with the core action and immediately provides the output format. Every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the simplicity of the tool (2 parameters, no output schema, no annotations), the description is largely complete. It explains the output format, which is crucial since there is no output schema. Minor missing details like behavior on invalid indices or empty tables.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with both parameters having clear descriptions (1-based indexing). The description adds no further meaning beyond the schema, so it meets the baseline of 3 but does not exceed it.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool reads all data from a table and returns it as a 2D array of strings. It uses a specific verb ('Reads'), a specific resource ('data from a table'), and specifies the output format, distinguishing it from sibling tools like set_table_data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use this tool (to read table data) but does not provide explicit guidance on when not to use it or alternatives. With sibling tools like set_table_data being obviously different, the lack of explicit when-to-use and when-not-to-use leaves room for improvement.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool lists animations for all items on a given slide, which is sufficient for a read operation. However, it does not mention any safety requirements, performance characteristics, or what happens for slides with no animations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that front-loads the action and scope. Every word contributes meaning, with no redundancy or filler. It is optimally concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given that the tool has only one parameter, no output schema, and no annotations, the description provides the essential information needed to use it correctly. It could be improved by noting that no animations exist if the list is empty, but overall it is complete for a simple listing tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema covers 100% of the parameter (slideIndex) with a clear description in the schema itself. The tool description does not add any additional meaning beyond 'given slide,' so it meets the baseline of 3 without adding extra value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Lists') and identifies the resource ('all build-in and build-out animations') clearly. It specifies the scope ('for every item on a given slide'), which distinguishes it from sibling tools like add_build_animation or remove_build_animation well.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving animations but provides no explicit guidance on when not to use it or alternatives. It assumes the agent will infer from the action, but without stating exclusions or prerequisites, it falls short of proactive guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the output includes position and size but does not detail behavior for invalid slide indices, empty slides, pagination, or limits. Adequate but lacks depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is front-loaded and contains no superfluous words. Every word adds value, making it highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity and complete schema, the description is mostly complete. It mentions output fields (position and size) but could specify whether shape names or IDs are included. The absence of an output schema is somewhat mitigated by the description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% for the single parameter. The description adds no extra meaning beyond the schema's documentation of slideIndex as a 1-based integer. Baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all shapes on a slide and specifies that it returns position and size information. This is a specific verb-resource combination that distinguishes it from sibling tools like add_shape or update_shape.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving shape details but provides no explicit guidance on when to use this tool versus alternatives, such as get_slide_content or list_text_items. No exclusions or context are given.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so the description carries the burden. It states the tool lists templates with details, but does not disclose if there are any limitations, authentication requirements, or default behavior (e.g., ordering). For a simple read-only list, it is adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
One concise sentence that front-loads the action and resource, with no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, no output schema, and no annotations, the description covers the essential information: what the tool does and what it returns. Missing details like format or count are not critical for a simple list tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters with 100% coverage, so the description need not add parameter details. The description implies the tool returns all available templates, which is sufficient.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('Lists') and resource ('presentation templates'), and adds details about what is included ('slide counts and descriptions'). It distinguishes from siblings like 'get_template' which likely returns a single template.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines2/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance on when to use this tool versus alternatives (e.g., 'get_template'). No context about prerequisites or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the basic save action and optional file path, but omits details like overwrite behavior, permissions, or return values. Adequate for a simple operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two concise sentences with no extraneous information. Front-loaded with core action and optional parameter. Perfectly efficient for the tool's simplicity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's low complexity, one optional parameter, and no output schema, the description covers essential behavior. Could mention overwrite behavior for completeness, but not strictly necessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 100% schema coverage, the schema already describes the filePath parameter. The description does not add new meaning beyond what the schema states, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'save' targeting the resource 'frontmost Keynote presentation' with optional save-as capability, distinguishing it from sibling tools like close_presentation and export actions.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for saving the current presentation, but lacks explicit guidance on when to use vs alternatives like export_to_pdf or close_presentation. No exclusions or when-not-to-use are mentioned.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full responsibility. It only states the action but does not disclose what happens if no slideshow is running (error vs. no-op) or any side effects. This is a significant gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence with no wasted words, perfectly front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with no parameters and no output schema. The description is minimally adequate but lacks details on prerequisites (e.g., slideshow must be running) or return value, which would be useful for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so the schema coverage is 100%. The description adds no parameter info, but baseline for zero params is 4.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Stops' and resource 'the currently running Keynote slideshow', clearly distinguishing it from sibling tools like start_slideshow and navigation commands.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly states the action of stopping a running slideshow, implying usage when the slideshow is active. No alternatives or exclusions are needed given the simplicity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses limited AppleScript support and that data series configuration may need manual adjustment, which are important behavioral traits beyond what schema shows.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with action, no wasted words. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, description covers key behavioral aspects (limitations) but could mention return value or error handling for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. Description adds a general caveat about data parameter requiring manual adjustment but does not enhance per-parameter meaning beyond schema descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Adds a chart to a slide' with specific verb and resource, and the mention of chart type setting distinguishes it from other add_ tools like add_image or add_shape.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides context about Keynote AppleScript limitations and potential need for manual adjustment, but does not explicitly state when to prefer this tool over alternatives or when not to use it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It correctly indicates the tool modifies the document ('changes the document theme, updating master slides and default styling') but does not mention whether changes are reversible, or whether all slides are affected. It is adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, minimal words (14 total), front-loaded with the core action. Every word is necessary. No redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool with no output schema, the description covers the essential: what it does and what it changes. It could hint that the theme must exist (listable via 'list_themes') but overall is sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% (the only parameter has a description). The description adds concrete examples ('e.g. 'White', 'Black', 'Gradient'') which helps the agent understand valid values beyond the schema. This adds meaningful value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb ('applies') and resource ('theme to current Keynote presentation'), clearly stating the action and scope. It distinguishes from sibling tools like 'list_themes' or 'change_slide_master' by explicitly mentioning applying to the entire presentation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description states what the tool does but provides no guidance on when to use it vs. alternatives, prerequisites (e.g., presentation must be open), or exclusions. With siblings like 'change_slide_master', some context on when to choose this over that would help.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses a key behavioral trait: 'Exports all slides to a temporary directory, then copies the specific slide image to the target path.' This reveals temporary side effects and inefficiency, which is valuable for an agent. However, it does not mention cleanup of the temp directory or potential errors.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, no redundancy. The first sentence states the core purpose, the second adds valuable behavioral context. Every word earns its place; the description is efficient and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations and no output schema, the description provides sufficient context for a simple export tool. It explains the mechanism and implies file creation. However, it lacks details on cleanup behavior, error conditions, or return value (e.g., success indication). Still, for a single-purpose tool, it covers the essential points.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all three parameters (format, filePath, slideIndex). The description adds minimal extra meaning beyond confirming the copy action for filePath. Baseline 3 is appropriate as it does not significantly enhance parameter understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action: 'Exports a single slide as an image file.' It specifies the resource (single slide), verb (exports), and output format (image file). The mechanism (export all slides then copy) further clarifies the tool's operation, distinguishing it from sibling export_to_images.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implicitly suggests use for single slide export, contrasting with export_to_images which likely exports all slides. However, there is no explicit guidance on when to use this tool versus alternatives, or mention of prerequisites like open presentation. The usage context is implied but not fully articulated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It describes the return structure but does not mention behavioral traits like idempotency, read-only nature, or potential latency. Since it's a retrieval tool, the lack of side-effect disclosure is a minor gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that efficiently lists all key return fields without any fluff. It is well-structured and front-loaded with the action and content summary.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description lists most return fields (name, slide count, theme, per-slide summaries with titles, body text, item counts, presenter notes). However, it does not mention if formatting details or exact positions are included, which is a minor omission given no output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, and schema coverage is 100%. The description does not need to add parameter information, so a baseline score of 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns a 'structured summary' of the entire presentation, listing specific fields (name, slide count, theme, per-slide summaries). This differentiates it from siblings like get_presentation_info and get_slide_content, which return partial data.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for obtaining comprehensive content but does not explicitly state when to use it versus alternatives (e.g., get_slide_content for a single slide). No 'when not to use' guidance is provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. Mentions persistence ('Values persist until changed or cleared'), but lacks details on idempotency, default behavior, or error handling. Could be more transparent about side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence that is front-loaded with purpose and includes key behavioral trait (persistence). No redundant information; every word earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Good for a simple setter tool with 7 optional parameters. Description covers purpose and persistence, but could mention that parameters are optional or that get_brand retrieves current settings. No output schema needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters3/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3. The description adds no extra meaning beyond the schema; it does not elaborate on defaults, interactions between parameters, or usage hints.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the tool sets brand configuration and affects subsequent design_slide and design_deck operations. The verb 'sets' and resource 'brand configuration' are specific, and it distinguishes from siblings like get_brand, design_slide, and design_deck.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states to use before design_slide and design_deck operations. Does not provide when-not-to-use or alternatives, but the context is clear given sibling tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It indicates a read operation ('gets') but does not mention side effects, authentication requirements, or data format. For a simple getter with no parameters, this is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that conveys the complete purpose without extraneous words. It is front-loaded and efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no parameters, no output schema, and a simple purpose, the description fully explains what the tool does and the source of data (active theme and overrides). It is complete for the tool's simplicity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so schema coverage is 100% trivially. Baseline is 4; the description adds no param info, which is acceptable given no parameters exist.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves the brand configuration from the active Keynote theme merged with overrides. It uses a specific verb 'gets' and identifies the resource, distinguishing it from the sibling tool set_brand.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for retrieving brand config, and the sibling set_brand suggests the alternative for setting. However, it does not explicitly state when to use this tool versus set_brand or provide any prerequisites or context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It lists common effects and points to the schema for parameters, but does not disclose what happens on success/failure, whether the transition replaces existing ones, or error behavior for invalid slideIndex. Some transparency is present, but lacking in depth.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no fluff: first states purpose, second provides examples and a helpful reference. Information is front-loaded and every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness3/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with 3 parameters and no output schema, the description is moderately complete. It covers purpose and parameter hints but omits behavior details like default duration, error handling, and return value. The schema provides constraints, but the description could add more context for completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, providing baseline of 3. The description adds value by listing common transition effects and referencing list_transition_types, enhancing the 'effect' parameter beyond schema. No extra info for duration or slideIndex, but the schema descriptions are sufficient.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Sets the transition effect for a slide', using a specific verb and resource. It distinguishes from siblings like add_build_animation and get_slide_transition by focusing on transitions. The list of common effects and reference to list_transition_types further clarify its purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides guidance on when to use this tool: to set a transition effect. It suggests using list_transition_types to see all available effects, which is helpful. However, it does not explicitly state when not to use it or mention prerequisites (e.g., slide must exist).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the return value is an array of objects with slideIndex and notes, which is helpful. However, it does not mention that the operation is read-only (non-destructive) or any potential errors, which is a minor gap. Given the simplicity, it is adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that conveys the purpose and return format without any waste. It is concise and front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no parameters and no output schema, the description adequately covers what it does and what it returns. It could hint at behavior for empty notes (e.g., returns empty array), but this is a minor omission. Overall, it is complete enough for an agent to use correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters in the input schema, and schema description coverage is 100% (since no params exist). Baseline is 4. The description adds no extra parameter information because none is needed, so it appropriately meets the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Returns presenter notes for all slides as an array of {slideIndex, notes}', which specifies the action (returns), resource (presenter notes), and scope (all slides). It naturally distinguishes from sibling 'get_presenter_notes' which likely returns notes for a single slide.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies when to use: when you need notes for all slides. However, it does not explicitly contrast with the sibling tool 'get_presenter_notes' (singular), which would be the alternative for a single slide. No explicit when-not-to-use or prerequisites are stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description bears full responsibility for transparency. It clearly states the read-only nature (returns a count) and scope ('frontmost presentation'), which is sufficient. No contradictions exist.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence with no wasted words. It immediately conveys the tool's purpose without any redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with no parameters, no output schema, and no annotations, the description is complete enough. It specifies what is returned and on which presentation. Could optionally mention the return type (integer), but it's not necessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There are no parameters, so schema description coverage is 100%. The description adds no parameter information, which is appropriate. According to guidelines, baseline is 4 for no parameters when coverage is high.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Returns the total number of slides in the frontmost presentation' uses a specific verb ('Returns') and resource ('total number of slides in the frontmost presentation'). It clearly distinguishes from sibling tools like 'list_slides' which would return slide details, not a count.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool works on the 'frontmost presentation' but does not explicitly state when to use it versus alternatives such as 'list_slides' or 'get_presentation_info'. No usage exclusions or context for when not to use are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It states what is returned but lacks details on behavior if slideshow is not started, side effects, or permissions. Adequate but could be more transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, clear sentence with no redundancy. Every word serves a purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately explains the return values (playing status and slide number). It could specify data types but is sufficient for a simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, schema coverage is 100% by default. The description adds no parameter info, which is acceptable per guidelines (0 params baseline 4).
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns the slideshow playing status and current slide number. It distinguishes from sibling tools like start_slideshow and stop_slideshow, which perform actions, making it a read-only status check.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Usage is implicitly clear: use to check slideshow state. While no explicit when-not or alternatives are given, the context of sibling tools provides natural differentiation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that the tool is read-only and returns presentation names and paths, but does not explicitly state it is non-destructive or mention any limitations like number of presentations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is front-loaded and concise, with no unnecessary words. Every part adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description must explain return values. It names the fields (names and file paths), but does not mention if presentation IDs or other metadata are included. For a simple listing tool, it is mostly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema is empty (no parameters), and schema description coverage is 100%, so the description does not need to add parameter context. The description adequately covers the tool's behavior without param details.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool lists all currently open Keynote presentations and specifies the returned information (names and file paths). This distinguishes it from sibling tools like open_presentation or close_presentation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use this tool versus alternatives is provided. The usage is implied by the simple listing purpose, but the description lacks context for when-not to use it or any prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It discloses the read operation and returned fields but does not mention edge cases (e.g., no open presentation) or performance characteristics. Adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that communicates the action and output clearly with no waste.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with no parameters and no output schema, the description adequately specifies the return structure. However, it could mention ordering or other details, but it is functionally complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no parameters and coverage is 100%. The description adds no parameter info, which is fine as none exist. Baseline 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns an array of all slides from the frontmost presentation, specifying the exact fields (index, title text, layout name). This clearly distinguishes it from sibling tools like list_shapes or get_slide_content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for listing slides in a presentation, which is clear for a zero-parameter tool. However, it does not explicitly state when not to use it or mention alternatives like get_slide_content for a single slide.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description reveals a key behavioral trait: it attempts a direct query and falls back to a curated list. This adds useful transparency beyond a simple 'list' statement, though it does not cover other aspects like caching or error behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that conveys the purpose and a key behavioral detail without any wasted words. It is appropriately concise.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's simplicity (zero parameters, no output schema), the description provides sufficient context about what it does and how it behaves. It could be more complete by mentioning the return format, but for a basic list operation it is adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so the baseline is 4. No additional parameter semantics are needed; the description correctly implies no user input is required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states that the tool 'lists available Keynote themes' and specifies the behavior (direct query with fallback). This distinguishes it from sibling tools like list_templates and apply_theme by focusing specifically on themes and their retrieval strategy.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide explicit guidance on when to use this tool versus alternatives. While it implies usage for viewing available themes, it lacks exclusion criteria or context for when to prefer list_themes over other related tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It states it returns a list of names but does not elaborate on format, any side effects, or whether the list is exhaustive. This is adequate for a simple read-only tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the main action, no filler words. Every sentence adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no output schema, the description adequately explains the return value as a list of transition names. It also links to the setter tool. Could mention if the list is sorted or includes aliases, but not necessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, so the description adds no parameter information. Baseline for 0 parameters is 4. The schema coverage is 100% trivially.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states it returns a list of Keynote slide transition effect names, which is specific and differentiates from other list tools. It also indicates the purpose for use with set_slide_transition.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly mentions that the names can be used with set_slide_transition, providing context for when to use this tool. However, it does not explicitly state when not to use or suggest alternatives, but the context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior3/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behavioral traits. It states the action but does not mention edge cases (e.g., at last slide, slideshow not active) or any destructive/read-only nature. For a 0-parameter tool, this is adequate but not thorough.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
Single sentence, no wasted words. Front-loaded with verb and object, immediately clear. Perfectly concise for a simple action.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness4/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple with no parameters and no output schema. The description covers the basic functionality. However, it lacks information about return values or error behavior, which would be useful for completeness. Given the minimal complexity, a 4 is reasonable.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
No parameters exist, and schema coverage is 100% (empty). The description does not need to add parameter info. With 0 parameters, a baseline of 4 is appropriate as no extra meaning is required.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Clearly states the action (advances) and resource (next slide or build) with context (during active slideshow). Distinguishes from sibling tools like previous_slide and go_to_slide by focusing on sequential forward movement.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly specifies the required context of an active slideshow, which tells when to use. Does not explicitly state when not to use or provide alternatives, but the sibling tools list is available and the condition is clear enough for safe invocation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description bears full responsibility for behavioral disclosure. It clearly states that the tool navigates to the previous slide or build, which is a simple action. An explicit mention of whether it wraps around or has no effect if already at the first slide would improve transparency, but the current description is adequate.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, concise sentence that front-loads the action and context. Every word is necessary and there is no redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Completeness5/5
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple navigation tool with no parameters and no output schema, the description is fully complete. It covers what the tool does and when it should be used (during an active slideshow). No additional information is needed.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters4/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and the schema coverage is 100% (empty schema). The description adds no parameter information, which is unnecessary given the lack of parameters. Baseline score of 4 is appropriate as the description does not need to compensate for schema gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly specifies the verb 'goes back' and the resource 'previous slide or build during an active Keynote slideshow'. It distinguishes itself from sibling tools like 'next_slide' and 'go_to_slide' by focusing on backward navigation within an active slideshow.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines4/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly states the prerequisite 'during an active Keynote slideshow', providing clear context for when to use the tool. While it does not list alternatives or when not to use, the sibling tools imply differentiation, and the condition is sufficient for correct usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

GitHub Badge

Glama performs regular codebase and documentation scans to:

Confirm that the MCP server is working as expected.
Confirm that there are no obvious security issues.
Evaluate tool definition quality.

Our badge communicates server capabilities, safety, and installation instructions.

Card Badge

Copy to your README.md:

[![keynoteMP MCP server](https://glama.ai/mcp/servers/superdwayne/keynoteMP/badges/card.svg)](https://glama.ai/mcp/servers/superdwayne/keynoteMP)

Score Badge

Copy to your README.md:

[![keynoteMP MCP server](https://glama.ai/mcp/servers/superdwayne/keynoteMP/badges/score.svg)](https://glama.ai/mcp/servers/superdwayne/keynoteMP)

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/superdwayne/keynoteMP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server