Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite no annotations, the description discloses atomicity, quota cost, and field mask warnings. It also specifies the return format including replies and warnings. It does not cover authentication or rate limits, but those are standard for the API. The description provides substantial behavioral context beyond what annotations would provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a summary, details, note, and clear args/returns. It is informative but compact for the complexity. A minor reduction in verbosity could improve conciseness, but it remains effective.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity and the presence of many sibling tools, the description is quite complete. It covers inputs, outputs, and key behavioral traits. It doesn't discuss error handling or retries, but the provided output schema (not shown) likely covers return values. Overall, it provides sufficient context for correct usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does so excellently: explains that presentation_id is the ID, and describes requests as a list of single-key Slides request objects with examples and a link to the full list. This adds significant meaning beyond the schema's bare types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool applies raw Slides batchUpdate requests atomically, distinguishes it as the low-level power tool, and lists example request types with a link to the API reference. It effectively communicates the core function and scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains that batching many edits costs a single write quota and warns about required fields masks for certain operations. It implies context for use but does not explicitly state when not to use or list alternatives, though the 'low-level power tool' phrasing helps differentiate from siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must convey behavior. It indicates a read-like operation ('summarize') and notes it is one call, but doesn't explicitly state safety or idempotency. Still, it's sufficiently transparent for this type of tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences: first describes functionality, second gives usage context. No extraneous words, front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers what the tool does and when to use it. It has an output schema, so return values are covered. Minor gap: no mention of prerequisites or limitations, but overall complete for a simple summarization tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is one parameter, presentation_id, with no description in the schema (0% coverage). The tool description does not elaborate on the parameter, but the parameter name is self-explanatory. Baseline for minimal additional value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool summarizes each slide with attributes like layout, element makeup, placeholders, and title. It also distinguishes itself by noting it is a single-call operation and suggests usage after copy_presentation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Use after copy_presentation to choose which showcase example slide to reuse for each section of the new deck,' providing clear when-to-use guidance and a specific context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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 explains that the copy preserves styling, masters, layouts, theme, and color scheme, and notes it's one call. However, it does not disclose potential issues like authorization needs or error handling for invalid source_id.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and well-structured: a brief summary, contextual explanation, and a clear Args list. Every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema (context confirms), the description adequately covers the tool's purpose, parameters, and usage scenario for a copy operation. It explains the high-fidelity template workflow, making it complete for agent selection.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description adds crucial meaning via the Args section, explaining source_id as the template ID, title as the new copy's title, and parent_folder_id as optional folder placement. This fully compensates for the schema's lack of description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool clones an entire deck using Drive files.copy, preserving full styling. It distinguishes itself from siblings like create_presentation by specifying it's for copying an existing deck with high fidelity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context as the starting point of a template workflow and explains the benefit of editing the copy like the showcase. However, it does not explicitly state when not to use this tool or suggest alternatives, but the context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description notes '1 API call' and explicitly states return values ({presentationId, title, url}). For a creation tool, this is transparent about scope and results, though no annotations are provided.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is succinct: a single sentence for purpose, then short args and returns sections. Efficient and front-loaded with key information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

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 an output schema, the description covers creation, returns, and API call count. It lacks prerequisites like authentication, but that is generally implied.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The single parameter 'title' is explained in the description: 'The title for the new presentation.' This adds meaning beyond the schema, which has 0% description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Create a new, empty Google Slides presentation', specifying the verb 'create', the resource 'presentation', and the empty nature. This distinguishes it from siblings like copy_presentation or duplicate_slide.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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 (e.g., copy_presentation, duplicate_slide). The description only states what it does, leaving the agent to infer usage from context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses '1 API call' efficiency and scope (slides or page elements), but lacks details on reversibility, permissions, or side effects. The name implies destruction, so it is minimally adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, followed by a specific usage note. Every word earns its place with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists, return value explanation is optional. However, the description omits important behavioral context like permanence, error handling, or batch behavior. It provides a use case and API call count but remains basic for a deletion tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so description must add meaning. It only says 'by ID,' which does not elaborate on presentation_id or object_ids format, constraints, or usage beyond what the schema already shows.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it deletes slides or page elements by ID. Verb 'delete' and resource 'slides or page elements' are specific, and the tool distinguishes itself from siblings like duplicate_slide or park_slides by focusing on removal.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit use case: 'prune the original showcase example slides after duplicating the ones you want.' This guides when to use it, though no explicit when-not or alternatives are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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 performance cost (2 expensive calls), the output format (normalized mismatch ratio and diff image), and the order of return (text summary then PNG). This is comprehensive, though it could mention idempotency or 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is four sentences, each earning its place: main action, cost, output detail, and use case. It is front-loaded with the core behavior and avoids unnecessary verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema (which covers return values) and sibling tools, the description provides sufficient behavioral and use-case context. It lacks parameter format details but is otherwise complete for a comparison tool with moderate complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% (only 'size' has a description). The description does not add meaning for the three required parameters (presentation_id, page_a, page_b). It implies page identifiers are slide IDs but does not clarify format or constraints, leaving a significant gap for agent use.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with 'Render two slides and report their pixel difference,' clearly stating the verb and resource. It distinguishes from sibling render_page (single slide rendering) and mentions a specific use case (verifying duplicated/edited slides), providing strong purpose clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description notes '(2 expensive calls)' to indicate cost and suggests usage for verifying slide matches. While it does not explicitly list when not to use or name alternatives, the context is clear and helpful for making an informed choice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must disclose behavior. It mentions 'full fidelity' and copying elements, but lacks details on error handling, permissions, or 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise, front-loaded with the main action, and each sentence provides value. No redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the output schema exists and the description covers key aspects, it is largely complete. However, edge cases and error handling are omitted, making it slightly less than fully comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description adds brief explanations for each parameter, clarifying insertion_index optionality. However, more detail (e.g., valid ranges, defaults) would improve.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool duplicates a slide within a deck with full fidelity, specifying the verb and resource. It distinguishes from siblings like reorder_slides and insert_text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a specific use case: instantiate a showcase example slide and then fill with replace_all_text. This gives context but does not explicitly exclude alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, but description discloses key behaviors: makes 1 API call, returns a bounded summary by default, and raw flag returns full untrimmed response. Implicitly read-only.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: one sentence describing purpose, one line about API call count, and a bullet list of parameters with no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Has output schema (not shown) so description only needs to hint at return behavior, which it does (bounded summary vs full response). Lacks error handling or edge case info, but acceptable for a simple getter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 0% parameter descriptions. Description only lists parameter names without explaining format or source for presentation_id and page_id. Only raw gets a brief explanation, which adds marginal value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb+resource: 'Get a single page (slide) as a bounded summary'. Differentiates from get_presentation (whole presentation) and list_slides (list of slide IDs).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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. Implies usage for a single slide summary, but does not distinguish from similar tools like render_page or list_slides for detailed work.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It explains default behavior (trimmed summary), the raw option, and that it uses 1 API call to keep output bounded. However, it does not explicitly state read-only nature or authorization needs, though 'Get' implies read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with about six sentences, front-loaded with the main purpose, followed by a note on the bounded output and then the parameter list. Every sentence adds value without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and an output schema present, the description adequately covers the tool's behavior and parameters. It explains the summary vs raw behavior and the bounded output. It could explicitly mention read-only or auth requirements, but overall it is mostly complete for an agent to decide usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so description must document parameters. It provides brief but meaningful descriptions for all three parameters: presentation_id ('The presentation ID'), include_masters ('Also summarize layouts and masters'), and raw ('Return the full, untrimmed API response instead of the summary'). This adds value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Get a presentation as a bounded, structured overview', specifying a specific verb and resource. It distinguishes from siblings by emphasizing the trimmed, summarized nature, contrasting with raw or other tools like get_page or list_slides.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context on when to use the raw parameter for full output versus the default summary, but does not explicitly compare to sibling tools like get_page or list_slides, or mention when not to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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 operation. It omits details on reversibility, element limits, or side effects on other elements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise but at the cost of informative content. It is front-loaded with the core action, but lacks necessary detail, making it borderline under-specified.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 required params, no annotations, output schema exists), the description is too minimal. It fails to clarify element requirements or result expectations beyond the single API call note.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must explain parameters. It does not mention 'presentation_id' or 'element_ids' at all, leaving their purpose and format entirely undocumented.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'group two or more elements into a single group', which is specific and distinct from sibling tools like 'ungroup_elements'. It also notes the single API call, adding precision.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool over alternatives like 'batch_update' or 'set_z_order'. No prerequisites or constraints mentioned, leaving the agent without context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations exist, so the description must cover behavioral traits. It only mentions '1 API call' for cost awareness but omits details on side effects, permissions, error handling, or behavior when index is out of range. 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with a parenthetical, front-loading the key action and including an efficiency note. Every word is essential, no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be explained. However, the description does not clarify how this tool fits with siblings, or prerequisites like the shape needing to exist. It covers the primary capability but leaves gaps in usage context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It clarifies that text is inserted into a shape or table cell, but does not explain individual parameters like element_id or index (e.g., 0-based). This adds moderate value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Insert' and resource 'text into a shape or table cell', and adds precision with 'at a character index'. This clearly differentiates from sibling tools like set_element_text or replace_all_text.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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 like set_element_text or replace_all_text. It lacks context for decision-making.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations, but the description discloses it is a lightweight read making one API call, implying no side effects. Could be more explicit about read-only nature, but 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two efficient sentences: first states action and output, second gives usage guidance. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With output schema present and only one required parameter, the description adequately covers the tool's purpose and lightweight nature, making it complete for this simple operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, but the single parameter 'presentation_id' is self-explanatory. The description adds no additional value beyond the schema, but given the parameter's clarity, a score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists slides with specific fields (index, id, layout reference) and distinguishes itself from deeper calls by noting 'only' and 'lightest-weight read'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly advises using it 'to find slide IDs before deeper calls', providing clear context and when-not-to-use alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It mentions '1 API call' and 'mark skipped', but does not disclose potential side effects, recovery options, required permissions, or rate limits. The description lacks sufficient detail about the tool's behavioral traits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences long and front-loaded with the action. Every sentence adds value: stating the action and efficiency, explaining the purpose, and giving a usage pattern. There is no redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the core usage but is incomplete. It references 'prune_parked_slides' but not 'unpark_slides', which is a related sibling. It does not mention the return value or any prerequisites. Given the tool's moderate complexity (2 required params, related siblings), the description is adequate but could be more comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 2 parameters with 0% coverage from the description. The description does not explain what 'presentation_id' or 'slide_ids' represent or provide format details. While the context implies slide_ids are the slides to hide, no explicit mapping is given, so the description adds minimal meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Hide slides (mark skipped)') and the resource, and distinguishes from siblings by specifying that slides stay as a clone source. It also references the related tool 'prune_parked_slides' for cleanup.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear guidance on when to use: to keep slides as a reusable palette while hiding them from presentation mode. It explicitly suggests duplicating from these slides and then calling 'prune_parked_slides' at the end. However, it does not explicitly state when not to use this tool or mention alternatives like 'unpark_slides'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Even without annotations, the description discloses destructive behavior ('Delete'), scopes to parked slides, and even notes API call limit (<=2). This gives good transparency beyond just the operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two short sentences with a parenthetical clarification and a usage note, all front-loaded with the core action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers what, when, and performance for a simple destroy operation. An output schema exists, so return details are not needed. The contextual info is complete given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only one parameter (presentation_id) and 0% schema coverage, the description does not elaborate on the parameter. However, the parameter's meaning is clear from context (the deck to clean up) and the tool's purpose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Delete') and resource ('every parked slide'), clearly defining the action. It also distinguishes from siblings like unpark_slides by stating it's a 'final cleanup' step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says to use it 'as the last step once the deck is assembled,' providing clear context. It does not mention alternatives or when not to use, but the intent is unambiguous.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

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 the call is expensive and returns the same image a viewer sees, but does not detail side effects, auth requirements, or the exact nature of the returned data (e.g., format, base64 encoding). This is adequate but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded: the first sentence states the purpose. It uses two paragraphs plus an args list, with no wasted words. Every sentence provides value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description does not have an output schema to rely on, so it should describe the return format. It mentions 'returns the server-side rendered pixels' but does not specify if it's a base64 PNG blob or binary data. With only 3 parameters and moderate complexity, more detail on the output would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds meaning beyond the schema: it explains 'presentation_id' as the presentation ID, 'page_id' as the slide object ID, and 'size' with illustrative pixel widths (LARGE ~1600px, etc.). The schema only provides a brief description for size, so the description significantly enhances understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'render', resource 'a slide', and purpose 'for visual verification'. It distinguishes from siblings by explicitly noting it's per-page and that the thumbnail endpoint is expensive, which aligns with the tool's role.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains the tool is used to confirm output looks correct and mentions it's a per-page operation with a cost implication. It does not explicitly name alternatives or when not to use, but provides sufficient context for an agent to infer appropriate use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits. It reveals that the operation is a single API call and implies moving slides. However, it fails to mention any side effects on other slides, required permissions, or whether changes are reversible. This is minimally sufficient 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: one sentence plus a parenthetical note. Every word adds value, and the key information is front-loaded. There is no redundancy or fluff.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

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 presence of an output schema (not shown), the description is adequate for a basic understanding but lacks details such as whether 'slide_ids' must be contiguous, what happens when 'insertion_index' is out of range, or any error conditions. The output schema might cover return values, but the description itself is not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, so the tool description must compensate. It hints that 'slide_ids' represent 'a block of slides' and 'insertion_index' is the 'new position'. However, it doesn't explain that 'presentation_id' is required, nor does it clarify ordering, indexing (0-based?), or constraints. The description adds some value but is incomplete.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('move a block of slides'), the resource ('slides'), and the destination ('new position'). It also notes it is a single API call, distinguishing it from batch operations. The sibling tools include duplicate and delete, so this purpose is well differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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 like 'duplicate_slide' or 'park_slides'. There is no mention of prerequisites, context, or when not to use it, leaving the AI agent without decision support.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full responsibility. It discloses that all replacements run in a single batch (one API call), which is useful. However, it does not mention potential side effects (e.g., overwriting formatting), permissions needed, or error behavior when placeholders are missing. The behavioral disclosure 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and front-loaded with a clear summary. The workflow context and parameter list are concise. Every sentence adds value without redundancy. Ideal structure for quick agent parsing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity (4 params, output schema present), the description covers the primary use case, batch behavior, and optional filtering. It does not address error conditions or permissions, but the essential information for correct invocation is present. The presence of an output schema reduces the need to describe return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must compensate. It explains the format and defaults for mappings, page_ids, and match_case. The presentation_id description is trivial but acceptable. Overall, it adds meaningful context beyond parameter names, though examples or constraints would improve clarity.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly specifies the action ('Replace all occurrences of each placeholder string'), identifies the resource ('placeholder text' in presentations), and distinguishes from siblings by positioning it as the 'primary content-fill tool for the template workflow.' This is specific and conveys a distinct use case.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides a clear use case (template workflow, mapping placeholder text to real content) and mentions batch operation. However, it does not explicitly state when not to use this tool or contrast with alternatives like insert_text or set_element_text. The context is clear but lacks exclusion guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It discloses that the tool reads the current transform once (to preserve scale/shear) and applies one absolute transform update, and mentions an API limit of up to 2 calls. This provides useful 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is moderately concise, with a clear initial statement followed by a docstring section. While not overly verbose, it could be streamlined slightly without losing clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (6 parameters, 4 required, no schema descriptions), the description thoroughly covers the behavior, parameter semantics, and transformation logic. The presence of an output schema reduces the need to document return values.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, so the description must add meaning. It provides a detailed docstring for each parameter, including optional semantics for width_pt and height_pt (preserve current if omitted). This fully compensates for the schema gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: setting an element's position (and optionally size) in points. It distinguishes itself from the sibling `update_transform` by positioning as a convenience for bounding box placement without matrix computation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains when to use this tool over `updatePageElementTransform` and notes it is a convenience method. However, it does not explicitly state when not to use it or provide direct comparisons to siblings like `update_transform`.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description reveals the internal mechanism: clears existing text then sets new text in one batch (deleteText + insertText). It also states safety on empty elements, offering full transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured but slightly redundant (mentions 'in one call' twice). The Args section is clear, and overall it's efficient without being overly verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple tool (3 string params) and existence of output schema, the description covers behavior, parameters, and use case. Missing error conditions but adequate for the context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description includes an Args section explaining all three parameters (presentation_id, element_id, text) with meaningful descriptions, compensating fully.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it replaces all text of a shape or table cell in one API call. It distinguishes itself from siblings like insert_text by specifying it replaces all text, and provides a concrete use case (filling duplicated slides).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description notes it's safe on empty elements and gives a specific use case. However, it does not explicitly mention when to avoid using it or provide direct comparisons to siblings like insert_text or replace_all_text, but the context is inferable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must convey behavioral traits. It mentions atomicity (1 API call) but does not disclose side effects, reversibility, error behavior for invalid element IDs, or whether the operation is destructive. 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise at one sentence plus a parenthetical. Every word is useful, but it could benefit from slightly more detail without being verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite the tool having 3 required parameters and no nested objects, the description lacks completeness. It does not explain the output (though output schema exists), return values, or error cases. For a tool that modifies a presentation, more context is needed about when changes take effect and how to undo.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33% (just the operation parameter has a description). The tool description does not add meaning for 'presentation_id' or 'element_ids' beyond their schema types. The operation parameter's possible values are listed in the schema but not explained in the description; the description only mentions 'front/back stacking order' without detailing each operation's effect.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: changing the front/back stacking order of elements. The parenthetical '(1 API call.)' adds atomicity. This distinguishes it from sibling tools like 'update_transform' or 'group_elements'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

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. Does not mention prerequisites, limitations, or when not to use it. For example, it doesn't clarify if this tool works on selected elements or requires prior grouping.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must carry full burden. It only states the operation and '1 API call', omitting side effects, permissions, or reversibility.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: one sentence plus a parenthetical note about API calls. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 0% schema coverage and no annotations, the description is too brief. Missing prerequisites, output implications, and context about ungrouping behavior.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, yet the description adds no meaning beyond parameter names. No explanation of 'presentation_id' or 'group_ids' format or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Ungroup' and the resource 'groups back into individual elements', distinguishing it from the sibling 'group_elements' tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use or avoid, nor comparison to alternatives like 'group_elements'. The description only states the action.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, description carries full burden. Mentions '1 API call' for efficiency but omits details like idempotency, side effects (e.g., error if slides not parked), or required permissions. Lacks transparency 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.

Is the description appropriately sized, front-loaded, and free of redundancy?

Short (2 sentences) but at expense of critical info. Efficient in length but under-specified for a tool with 2 required parameters and no annotation support.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema and 2 params, description fails to explain return structure or behavioral details. Minimal context leaves agent with gaps for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, yet description provides no parameter explanations. Agent must infer that presentation_id and slide_ids are needed but no guidance on format or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states action (unhide slides) and target (previously parked slides). The verb 'unhide' and phrase 'mark not skipped' precisely define the operation, distinguishing it from sibling tools like park_slides.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Implied as inverse of park_slides, but no explicit when-to-use or when-not-to-use guidance. Sibling names provide context but description itself lacks direct alternatives or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description bears full burden. Discloses it is 1 API call and the transform modes (absolute/relative), but does not detail side effects, permissions, or behavior beyond input.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise and well-structured with the main action first, followed by args. Minor verbosity in the Args block but overall efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers core purpose and parameters adequately. Output schema exists but description does not mention return values. Still, it is sufficient for a mutation tool with clear input.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25%, but description compensates by detailing the AffineTransform fields (scaleX, scaleY, etc.) and the mode parameter values (ABSOLUTE/RELATIVE).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Apply a raw AffineTransform to an element', specifying the action and resource. The sibling tools do not directly perform affine transforms, so it is distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use versus alternatives. The description implies usage for applying raw transforms but lacks when-not or alternative recommendations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.