Ghost Styling MCP

Server Quality Checklist

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

Latest release: v0.1.0
Disambiguation5/5
Each tool has a clearly distinct purpose, with detailed descriptions that prevent confusion between similar operations (e.g., publish_post vs update_post, create_theme vs upload_theme vs activate_theme). The boundaries between content types (post/page/member/newsletter) are well-defined.
Naming Consistency5/5
All tools follow a consistent verb_noun snake_case pattern (e.g., create_post, list_members, update_theme). Even longer names like upload_image_from_url adhere to the same scheme. No mixing of casing or irregular verbs.
Tool Count2/5
55 tools is excessive for a single MCP server, especially one focused on 'Styling'. The server includes full CRUD for many Ghost entities (members, offers, newsletters, etc.) well beyond styling, making the surface overwhelming and the scope unfocused.
Completeness4/5
The tool set covers the full styling workflow (extract brand → create/restyle/preview/upload/activate theme) and basic CRUD for most content types. Minor gaps exist (no delete_theme, delete_newsletter only via archive, no user management) but these are often API limitations.
Average 3.9/5 across 55 of 55 tools scored. Lowest: 2.8/5.
See the Tool Scores section below for per-tool breakdowns.
- No community issues in the last 6 months
- 42 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
This repository is licensed under MIT License.
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

Behavior2/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description must disclose behavior. It indicates a safe read operation, but fails to mention error handling, permissions, or rate limits. The existence of an output schema somewhat mitigates this, but the description adds 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 a single sentence with no wasted words. However, it is somewhat under-specified for the tool's complexity, balancing conciseness with completeness.
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, existing output schema, and no annotations, the description is adequate for a simple read tool. However, it lacks usage guidance and parameter details, leaving an agent to infer too much.
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 description implies the member_id parameter by stating 'by id', but does not specify format, constraints, or examples. With 0% schema description coverage, the description should compensate, but it only minimally clarifies the parameter's role.
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 it reads a single member by ID and lists included entities (labels, newsletters, tiers). This distinguishes it from list_members and other get tools, but does not explicitly differentiate from siblings like get_label or get_newsletter for specific 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 guidance on when to use this tool versus alternatives such as list_members or other get tools. No exclusions or prerequisites 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 only mentions listing active and archived newsletters, missing details about pagination defaults, limit constraints, sorting, or filtering behavior. Minimal 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 extremely concise (two words plus parentheses) and front-loaded. It efficiently conveys the core purpose without unnecessary words. Slightly too terse but earns points for brevity.
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 list tool with output schema, the description is minimally adequate. It covers the basic listing of newsletters but omits guidance on pagination and filtering. With 4 parameters and an output schema, some 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 description coverage is 100%, so parameters are fully documented in the schema. The tool description adds no additional meaning beyond what the schema provides. Baseline 3 is appropriate.
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 specifies the verb 'List' and resource 'newsletters', and distinguishes that it includes both active and archived newsletters. This differentiates it from get_newsletter (single newsletter) and create/update tools. However, it could mention that it returns a paginated list.
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 get_newsletter or other list tools. The description only 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 and a terse description, the tool fails to disclose behavioral traits like read-only nature, pagination behavior (implicit in schema), or any side effects. The description carries the full burden but offers no insight beyond the verb.
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 extremely concise with no redundant words. However, it borders on under-specification; a sentence or two more would enhance usability without sacrificing conciseness.
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 4 parameters, no required fields, and an output schema, the description is minimally viable. It lacks contextual hints about features like pagination, filtering, or ordering (present in schema) but the schema compensates partially. The description could be more informative for a complex 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 already provides complete descriptions for all 4 parameters (100% coverage). The description adds no additional meaning beyond what the schema conveys, thus meeting the baseline expectation without providing extra value.
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 (list) and resource (blog posts), making the primary purpose obvious. It distinguishes from sibling list tools like list_pages or list_labels. However, it lacks any additional context about scope or filtering, leaving room for ambiguity about what 'list' entails.
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 get_post, list_pages, or search-related tools. There is no mention of prerequisites, context, or exclusions, leaving the agent to infer usage 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?
With no annotations, the description carries full behavioral disclosure burden. It only states it's an update with partial changes, but omits details like return value, error handling, authorization, or reversibility. The presence of an output schema is not mentioned.
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 extremely concise with a single, front-loaded sentence containing the essential action and partial update behavior. However, it could be slightly expanded to mention the output or a hint without losing conciseness.
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 7 parameters, no schema descriptions, and no annotations, the description is too sparse. It does not cover return values, error scenarios, or parameter relationships. The existence of an output schema reduces the need for return value explanation, but overall completeness is low.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
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 explanation for any of the 7 parameters (name, slug, tag_id, etc.). It fails to compensate for the lack of schema descriptions, leaving parameter meaning entirely to the schema property names.
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 (Update), the resource (a tag), and the identifier (by id). It also specifies partial update behavior ('only the fields you pass are changed'), distinguishing it from create, delete, or full replacement tools.
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 use for modifying existing tags but does not explicitly mention when to use this tool over siblings like delete_tag or create_tag. No alternatives 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?
With no annotations, the description must carry behavioral disclosure, but it only states the basic action. No details on side effects, auth needs, or constraints like unique name.
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?
A single, front-loaded sentence with no wasted words. However, given the tool's complexity, a bit more detail would be justified without harming conciseness.
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 a detailed schema and output schema, the description omits context like validation rules (unique name), behavior on duplicate, or relationship to list_tiers, making it incomplete for complex 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%, so parameters are fully documented in the schema. The description adds no extra semantic value beyond what is already there.
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 'Create a discount offer against a tier' uses a specific verb and resource, clearly distinguishing it from siblings like update_offer or list_offers.
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_offer, or any prerequisites like having a tier first.
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 disclose behavior. It only states 'This cannot be undone' (permanence), missing other possible side effects, permissions, or error conditions.
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?
Extremely concise: two sentences, front-loaded with the action, no wasted 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?
Despite having an output schema, the description does not explain return values. It lacks usage context and behavioral details beyond permanence, making it incomplete for a delete operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0% and the description adds no meaning to the 'post_id' parameter beyond its type and required status.
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 ('Delete') and resource ('a post') with identifier ('by id'), and it is distinct from sibling tools like create_post or update_post.
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 use when deletion is intended but provides no explicit guidance on when not to use it or alternatives.
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 the full burden. It only states the tool is a read operation and includes prices and benefits, but lacks disclosure of authentication needs, error handling (e.g., not found), rate limits, or other 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single concise sentence that front-loads the key information (read by ID, includes prices and benefits). No unnecessary words or repetition.
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 output schema exists, the description does not need to detail return values. It adequately specifies the input and output scope. However, it could be more complete by mentioning behavior on missing IDs or error states.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters1/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description does not add any meaning beyond the input schema. The schema has 0% description coverage and only provides the parameter name tier_id. The description never elaborates on the parameter's format, constraints, or role.
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 a single tier by ID and includes prices and benefits. It distinguishes from sibling tools like list_tiers (list all) and update_tier (modify) by specifying a unique operation and output details.
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 explicit guidance on when to use this tool versus alternatives (e.g., list_tiers). The usage is implied but not stated, and no exclusions or prerequisites 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 that the tool supports pagination, sorting, or that it is a read-only operation. The agent must infer behavior solely from the schema.
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 with no unnecessary words. It is appropriately sized for a simple list tool.
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 presence of an output schema, the description is minimally adequate. However, it lacks context about pagination defaults, sorting behavior, and whether labels are listed globally or per member.
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 additional meaning beyond what the schema already provides for page, limit, and order.
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 'List member labels' clearly states the tool's purpose with a specific verb and resource. However, it does not explicitly differentiate from sibling list_* tools (e.g., list_tags, list_posts) or specify the scope (e.g., 'all' vs. filtered).
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 usage guidance is provided. The description does not indicate when to use this tool versus alternatives like get_label (for a single label) or other list tools. There is no mention of prerequisites or 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 present, so the description carries the full burden. It does not disclose pagination behavior, authentication needs, rate limits, or any side effects. The minimal description assumes basic read behavior but omits crucial operational details.
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 extremely concise—one short sentence. It avoids redundancy and gets straight to the point. However, it could be more structured (e.g., bullet points for key features) without losing brevity.
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 an output schema and well-documented parameters, the description lacks behavioral and usage context. For a list tool with many sibling tools, more detail is needed to ensure correct selection and 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?
The input schema has 100% coverage, so the baseline is 3. The description adds no parameter-specific meaning beyond what the schema already provides. The mention of 'how many posts use each' is not directly linked to any parameter (e.g., 'count.posts' in 'order').
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 ('List tags') and includes the key feature ('with how many posts use each'). It distinguishes the tool from siblings like list_posts or list_members by specifying the resource (tags) and the additional count information.
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., filtering vs. browsing, pagination limits). The description does not mention any prerequisites, exclusions, or comparative context with other list 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 provided; description lacks behavioral details like pagination behavior, rate limits, or response format beyond 'prices and benefits'. Relies on schema for parameter 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?
Single sentence, front-loaded with verb and resource, 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?
Minimal but functional for a simple list operation. Output schema exists, but description could mention pagination or default limit. Adequate overall.
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 parameters are well-documented. Description adds no extra meaning beyond what schema provides, earning baseline 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?
Clearly states it lists tiers (paid plans) with prices and benefits. Distinguishes from get_tier and create_tier, but does not explicitly differentiate from other list 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 on when to use this vs other list tools or alternatives like get_tier. No context about prerequisites 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 fully bears the burden of behavioral disclosure. It only states the purpose, omitting critical traits like read-only nature, pagination behavior, rate limits, or whether results are sorted/filtered.
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 efficiently conveys the purpose. While it lacks structure (e.g., sections), it wastes no words and 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?
For a simple list tool with a full schema and an output schema, the description is adequate but lacks context about the nature of 'offers' (e.g., active vs. expired) and any implicit filtering. It meets minimal completeness but has clear gaps.
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 each parameter already described in the schema. The description adds no additional meaning beyond what the schema provides, meeting the baseline expectation.
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 action ('list'), the resource ('discount offers'), and adds a distinguishing detail ('each with its linked tier'). This differentiates it from sibling tools like 'list_tiers' or 'list_posts'.
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. There is no mention of scenarios where this tool is preferred or excluded, leaving the agent without explicit selection criteria.
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 exist, so the description carries the full burden. It explains price unit conventions and output but omits safety-related behaviors (e.g., whether creation is reversible, auth requirements, or rate limits).
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 four sentences in one paragraph, front-loading the core purpose. It is efficient but could be slightly more structured with bullet-style insights for parameters.
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 9-parameter complexity and presence of an output schema, the description addresses core constraints (price units, currency) but lacks explanations for many optional fields and potential restrictions, leaving moderate gaps.
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?
Input schema has 0% description coverage, yet the description only clarifies three parameters (name, currency, benefits, and price units) out of nine. Remaining parameters like trial_days, visibility, welcome_page_url are left undocumented.
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 begins with 'Create a tier (paid plan).' which clearly identifies the action and resource, and the parenthetical disambiguates from other tier-related tools like 'list_tiers' or 'update_tier'.
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_tier' or other creation tools. There are no prerequisites, conflicts, or contextual examples.
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 disclose behavioral traits. It only states 'Read', implying safety, but does not address permissions, error handling, idempotency, or rate 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 sentences with no wasted words. The first sentence front-loads the purpose, and the second covers parameter usage. Ideal conciseness.
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 output schema exists, return values are covered. However, the description does not mention authentication needs, rate limits, or how this tool differs from similar get_* 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?
Schema coverage is 0%, so the description must add meaning. It clarifies that the two parameters are alternatives (either/or), but lacks details on format, constraints, or usage context.
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 ('Read') and resource ('a single user'), and specifies the two identifiers (id or slug). It is distinguishable from siblings that target different resources like get_member.
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 to provide either user_id or slug, which is helpful, but does not explicitly detail when to use this tool over alternatives like list_users.
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 only says 'Read' with no mention of side effects, authentication, or error handling beyond the implicit read-only nature.
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 redundancy or 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?
Minimal but sufficient for a simple one-parameter read tool with an output schema; lacks details on return value or edge cases.
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 parameter 'newsletter_id' is self-explanatory, but the description adds no additional semantics (e.g., format, example) 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.
Purpose5/5
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states the action ('read') and resource ('a single newsletter by id'), distinguishing it from sibling tools like list_newsletters and create_newsletter.
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, but the simple read operation implies straightforward 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?
Discloses partial update behavior ('only the fields you pass are changed'), which is helpful, but lacks details on reversibility, authorization, or side effects; no annotations provided to offload burden.
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 14 words, front-loaded with action and object, no redundancy.
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?
Output schema exists, so return values are covered, but for a mutation tool, more completeness is expected to ensure safe invocation (e.g., error handling, idempotency).
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 has 0% description coverage, and the description does not explain the meaning of parameters (label_id, name, slug) beyond their names; no added 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?
Explicitly states 'Update a label by id' using a specific verb and resource, clearly distinguishing it from sibling tools like create_label, delete_label, get_label.
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?
Provides no guidance on when to use this tool versus alternatives (e.g., create_label, delete_label) and no 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?
With no annotations, the description must fully explain behavior. It mentions return value ('Returns the created tag's summary'), which is good, but omits other behavioral traits like required permissions, side effects, or error conditions. 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?
The description is extremely concise with two sentences, no filler, and front-loads the core purpose. Every sentence adds value, making it efficient for an AI agent to parse.
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 6 parameters and an output schema, the description covers the essential behavior (creation, required field, return). However, it omits details on optional parameters and does not address potential pitfalls or advanced usage, making it 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 description coverage is 0%, so the description must compensate. It clarifies that 'slug' is derived from 'name' if omitted, adding meaning beyond the schema. However, the remaining four parameters (meta_title, description, etc.) receive no explanation, leaving semantic gaps.
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 creates a tag, distinguishing it from sibling tools like create_label or create_post. It specifies the required resource (tag) and the minimal requirement (name only), giving precise purpose without ambiguity.
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 provides helpful guidance on parameter usage (only name is required, slug is derived). However, it lacks context on when to use this tool versus alternatives (e.g., create_label for labels), relying on the tool name alone for differentiation.
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 mentions that members are not deleted, which is a key behavioral trait. However, it lacks details on permissions, reversibility, or error scenarios. With no annotations, the description partially fulfills this need.
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 that are front-loaded with the action and include a clarifying behavioral note. No wasted 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?
For a simple delete tool with one parameter and an output schema present, the description covers the essential effect on associated members. Minor gap: no mention of idempotency or confirmation of deletion.
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 only parameter label_id is not described beyond its existence in the schema. With 0% schema coverage, the description should provide context like where to obtain the ID or format, but it does not.
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 'delete a label by id' and specifies that members retain their existence but lose the label, distinguishing it from other label-related 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 on when to use this tool versus alternatives like update_label or list_labels. No prerequisites or exclusions 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 provided, so description carries full burden. Only mentions 'newest first' which matches default order. Does not disclose pagination behavior, authorization needs, rate limits, or side effects (though likely read-only). More detail needed.
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, front-loaded with key info, 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?
Output schema exists, so return value explanation is not needed. Description is brief; could mention pagination defaults and filter syntax briefly. For a 4-param tool with no annotations, minimally 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 covers all 4 parameters with descriptions (high coverage). Description adds context about included fields (labels, newsletters) but not substantial beyond schema. 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?
Clearly states action (list), resource (members), sorting order (newest first), and included data (labels, newsletters). Distinct from sibling tools like get_member or list_posts.
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?
Implied usage: use for listing members. No explicit guidance on when not to use (e.g., for single member use get_member) or comparisons with other list 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 must disclose behavior. It correctly implies a read-only operation, but does not mention any side effects, permissions, or pagination details beyond what the schema provides. Minimal but 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?
Single sentence that directly states the purpose and distinguishes from posts. No filler, every word contributes.
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 and has an output schema, so the description does not need to explain return values. However, it lacks guidance on usage context compared to sibling tools and omits any behavioral disclaimers. 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% with each parameter described. 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 'List' and resource 'pages', and clarifies that these are standalone content outside the post feed, effectively distinguishing from the sibling tool 'list_posts'.
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_posts), no prerequisites, and no examples. The description only states the basic function, leaving the agent without decision criteria.
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 that deletion cannot be undone, which is key behavioral info. However, it omits details like required permissions, cascading effects, or error conditions, leaving gaps in transparency.
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, using two short sentences with no redundancy. The critical information (action and irreversibility) is front-loaded, making it efficient for an agent to parse.
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 is a simple delete operation with one parameter and an output schema exists, the description covers the essential purpose. However, it lacks context about permissions, error handling, or what happens to related content, which is moderate completeness for a mutation tool.
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 description coverage is 0%, meaning the properties (page_id) have no descriptions in the schema. The description adds only 'by id', which vaguely hints at the parameter's role but does not explain format, examples, or constraints. With one parameter, a more informative description is expected.
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 explicitly states the verb 'delete' and the resource 'page by id', making the tool's purpose unmistakable. It clearly distinguishes from sibling delete tools (e.g., delete_label, delete_post) which 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 Guidelines3/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description mentions irreversibility but provides no explicit guidance on when to use this tool versus alternatives or any prerequisites. Usage is implied by the resource name but lacks context like 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, so the description must carry the full burden of behavioral disclosure. It only mentions parameter behavior (slug derivation) without addressing side effects, permissions, or mutation implications. This is insufficient 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.
Conciseness5/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is efficient and front-loaded with the purpose. Every word earns its place without redundancy.
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 and the existence of an output schema, the description is minimally adequate. However, it does not explain the return value or any potential side effects, leaving gaps for an agent to infer.
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 has 0% parameter descriptions, so the description must compensate. It adds that name is required and slug is derived if omitted, which adds meaning beyond the schema types. However, it does not explain what slug means or any constraints.
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 'Create' and the resource 'member label'. It distinguishes itself from sibling tools like update_label, delete_label, and list_labels, ensuring the agent knows this is for creation.
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?
While the description does not explicitly mention when to use or exclude alternatives, the context is clear: use this tool to create a new label. No counterexamples or prerequisites are given, but the purpose is straightforward.
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 correctly indicates a read operation with no side effects, but fails to disclose behavior on missing IDs, access restrictions, or return format details beyond 'linked tier'.
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?
Extremely concise: one sentence, no redundancy. Every word adds value, including the detail about the linked tier, which enhances understanding without bloating the description.
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 straightforward read tool with an output schema, the description is nearly complete. It specifies the return includes the linked tier, but omits potential error states or behavior for non-existent IDs. Still, it adequately covers the essential functionality given the tool's simplicity.
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 0% and the description does not elaborate on the required 'offer_id' parameter. Although the parameter name is self-explanatory, the description should provide context on format or expected values. With one parameter, a baseline of 4 would apply if it were documented, but here it is not.
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 ('Read a single offer by id') and the resource ('offer'), and adds specific context ('including its linked tier'). It efficiently distinguishes from sibling tools like list_offers (which returns multiple) and create/update offers.
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 context implies using this tool for a single offer (vs. list_offers for multiple), the description lacks information on prerequisites, error handling, or scenarios where other tools would be more appropriate.
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?
Without annotations, the description carries the full burden. It discloses that posts keep existing after tag deletion, which is important non-obvious behavior. However, it omits information about permissions, error handling, or idempotency.
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: first states the action, second clarifies the effect. No filler 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 delete tool with one parameter, the description covers the essential effect. However, it lacks information about return values, error conditions, or what happens if the tag_id does not exist, leaving gaps for an agent.
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 has 0% description coverage for the 'tag_id' parameter. The description only says 'by id', adding minimal meaning beyond the schema's definition of a required string. It does not compensate for the lack of parameter documentation.
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 'Delete a tag by id', specifying the action (delete) and resource (tag). It further clarifies that posts keep existing, which distinguishes it from destructive deletion that might cascade.
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 the tool (to delete a tag without affecting posts) but does not explicitly state when not to use it or provide alternatives among sibling tools like 'create_tag' or 'update_tag'.
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 states the tool updates a field and returns updated fields, but lacks details on permissions, side effects, or destructive potential. The behavior is minimal and clear for a simple update.
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?
Three concise sentences: purpose, parameter explanation, and rationale/return info. Front-loaded with the action, no wasted words.
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 single-parameter tool with an output schema, the description adequately covers purpose, parameter format, and return value. No additional context is 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?
Schema description coverage is 0%, so the description compensates by explaining that accent_color is a hex value and providing an example. This adds meaning beyond the schema's type definition.
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 updates the blog's brand accent colour, a specific verb-resource pair. Among many update siblings, this one is distinguished by targeting the brand accent colour specifically.
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 explicit guidance on when to use this tool versus alternatives like 'restyle_theme' or other update tools. It only hints at keeping alignment with the main site, which is implicit.
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?
Transparently describes the partial update behavior and that it returns the updated fields. With no annotations, it adequately covers the nondestructive nature. Could mention if changes are reversible.
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?
Three concise sentences, front-loaded with purpose, no redundancy. 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 10 optional parameters, no annotations, and an output schema, the description covers purpose, partial update, and return value. Could mention authentication or rate limits, but not essential for this 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?
Schema coverage is 0%, so description compensates by grouping parameters into categories (title/description, meta, OG, Twitter). However, individual parameter constraints or formats are not defined, which is acceptable given the schema's simplicity (all strings).
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?
Description clearly states the tool updates the blog's identity and SEO/social metadata, listing specific field groups (title, meta, OG, Twitter). However, it does not explicitly differentiate from sibling tools like update_branding.
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?
States that only provided arguments are changed (partial update). No explicit guidance on when to use this tool vs. alternatives, 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.
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 that the download goes to a local temp file and returns path and size. It does not cover permissions, rate limits, or possible side effects, but the basic behavior is adequately described.
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 two sentences with no wasted words. The main action is front-loaded, and additional details are presented efficiently.
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?
With a single parameter and an output schema presumably present, the description covers what the tool returns (path and size). It is complete for a simple download operation, though it could mention authentication requirements.
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 one parameter 'name' with a clear description. Schema coverage is 100%, so baseline is 3. The description does not add extra semantic meaning beyond the schema, which is acceptable.
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 'Download', the resource 'installed theme's source as a ZIP', and the target 'local temp file'. It distinguishes from sibling tools like 'upload_theme' and 'preview_theme'.
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 context by stating 'Useful for grabbing a theme's assets, branding, or package.json as a reference.' While it doesn't explicitly list when not to use or alternatives, the context is clear for the intended use case.
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 present, so description alone must disclose behavior. It indicates read-only, includes rendered HTML and preview_url, but lacks info on error handling or rate 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 sentences, front-loaded with core action, no redundant 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?
Output schema exists, so return value details are not required. Description still mentions key outputs (rendered HTML, preview_url). Adequate for a simple read 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?
With 0% schema description coverage, description adds value by stating mutual exclusivity of parameters, but does not explain format or constraints beyond that.
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 'Read a single post by id or slug' with specific verb and resource, differentiating it from list/create/update/delete siblings.
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 tells to provide either post_id or slug, guiding parameter selection. No explicit when-not-to-use, but context implies it's for single post retrieval.
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. Describes read operation and return fields but does not state idempotency, side effects, or authentication requirements. Minimal behavioral context beyond the verb 'Read'.
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 purpose, then details. Every sentence adds value with 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?
Covers purpose, return data, and usage context. Lacks error handling or authentication notes, but for a simple read tool with output schema, it is sufficiently 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?
No parameters exist, so schema coverage is trivially 100%. Per guidelines, baseline is 4 for zero params. Description adds no param info but none needed.
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 blog brand and SEO settings, specifying verb 'Read' and resource 'blog's brand and SEO settings'. It distinguishes from siblings like update_branding and get_post by focusing on brand/SEO metadata.
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 recommends using to 'review the current state before updating' and 'keep the blog aligned with the main site', providing clear context. Does not list exclusions or alternatives, but the usage scenarios are well-defined.
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 discloses key behaviors: partial update, status effects, and html never blanks. It could mention idempotency or reversibility but adequately covers essential mutation behaviors.
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?
Three concise sentences, front-loaded with the main purpose, no filler. 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?
Given 9 parameters and an output schema, the description partially covers update semantics but lacks detail on most parameters. The principle 'only fields you pass are changed' provides general context, but specifics are missing.
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 description coverage is 0%, so description must compensate. Only status and html are explained; the other 7 parameters (title, tags, excerpt, etc.) have no semantic description, leaving a significant gap.
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 'Update an existing post by id' with a specific verb and resource, distinguishing it from sibling tools like create_post, publish_post, delete_post.
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?
Provides guidance on when to use, especially for publishing/unpublishing via status and how html is handled. However, it does not explicitly mention when not to use or alternatives like publish_post.
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 upload action and return, but does not mention file size limits, overwrite behavior, or privacy implications. Adequate for a straightforward upload 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?
Two sentences, front-loaded with the core action followed by usage guidance. Every sentence adds value without 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?
Given that an output schema exists, the description need not explain return values. It covers purpose and usage adequately, though it omits file size limits or error handling. Overall complete for a simple upload 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%, baseline 3. The description adds limited new context: the square requirement for 'profile_image' and 'icon' is already in the schema. No additional parameter semantics are provided 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 uses the verb 'Upload' and specifies the resource 'local image file to the blog,' with a clear return of a hosted URL. It differentiates from the sibling tool 'upload_image_from_url' by emphasizing 'local' upload.
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 where the returned URL can be used (feature_image, logo/icon via update_branding, newsletter header_image). It provides context but lacks explicit when-not-to-use or alternatives, though the sibling list suggests alternatives.
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?
Discloses key behavior: packages directory, uploads, installs without activation, returns validation errors/warnings. However, no annotations exist, and it omits details like idempotency, overwrite behavior, required permissions, or rate 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 sentences, front-loaded with the key disambiguation (not activating), no filler. Every sentence provides essential 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?
Tool has only one parameter, output schema exists, and description covers outcome and error handling. Missing overwrite behavior or theme ID return, but sufficient for an upload tool with clear purpose.
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 description adds minimal value beyond the schema by implying packaging of the directory. The schema already describes theme_path as 'Path to the theme directory to upload.'
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 uses specific verb 'upload', resource 'theme', and explicitly states 'WITHOUT activating it', clearly distinguishing from sibling tools like activate_theme and create_theme.
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?
Clearly explains that the theme is installed but inactive, allowing manual review and activation, and mentions validation on upload. However, it does not explicitly differentiate from other upload tools like upload_image or create_theme.
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 accurately describes the read-only listing behavior but does not disclose authorization needs, rate limits, or other traits. For a zero-parameter tool, this is minimally sufficient.
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, front-loaded with the action and result. No unnecessary words.
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 zero parameters and presence of an output schema, the description clearly states what the tool returns (themes and active one). Complete for a 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?
No parameters exist, so the description does not need to add parameter semantics. Baseline score of 4 applies as per guidelines.
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 lists installed themes and identifies the active one, with a specific verb and resource. It distinguishes from siblings like activate_theme and create_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?
No explicit guidance on when to use this tool versus alternatives, but the context of listing installed themes is implied. No exclusions or alternatives mentioned, but for a simple list tool this is adequate.
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 effectively discloses critical behaviors: set replacement for arrays and unsubscription behavior. It does not mention potential side effects like email change implications, but it is mostly 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?
Two concise sentences with a note, front-loaded with purpose, no redundant information. Every sentence adds value.
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?
Output schema exists, so return format is covered. However, missing parameter descriptions for name, note, email, and no mention of error cases or prerequisites. Adequate for a standard update but has gaps.
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 0%, so the description must add meaning. It explains the behavior for 3 of 7 parameters (labels, newsletter_ids, subscribed) but omits name, note, email, and member_id. Partial coverage is adequate but not complete.
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 'Update a member by id' and specifies that only passed fields are changed, distinguishing it from create, read, and list member tools.
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?
Provides explicit behavioral notes about replacement semantics for labels and newsletter_ids, and the effect of subscribed=false. Does not explicitly state when to use vs alternatives but context is clear.
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 carries full burden. It discloses default status (draft), tag auto-creation, meta field handling, and return includes preview_url. It does not mention rate limits, authentication, or destructive consequences beyond creation, but the core behavioral traits are well communicated.
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 three sentences (after the first line) and uses line breaks for readability. It is front-loaded with the main action, and every sentence provides essential information without redundancy. No filler 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 the 8 parameters, 1 required, no annotations, and an output schema exists, the description covers creation flow, default status, tag creation, and return summary. It could mention the behavior for excerpt or feature_image, but overall it provides a solid understanding of the tool's functionality.
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 0%, so description must explain parameters. It covers html (implied from 'HTML content'), tags (created if not exist), status (default and publish option), meta_title/meta_description (search metadata). However, it omits details for excerpt, feature_image, and the html default empty string. The description adds meaning but leaves some 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 states 'Create a blog post from HTML content', specifying the verb (create) and resource (blog post). It adds unique details like draft default and publishing behavior, which distinguish it from siblings like create_page or publish_post. The sibling list includes create_page and publish_post, but the description makes the tool's role explicit.
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 explains when to use: creating a new blog post, with default draft behavior and an option to publish immediately. It mentions tag creation and meta fields. However, it does not explicitly contrast with sibling tools like create_page for pages or publish_post for publishing drafts, so an agent might not know the best alternative in all contexts.
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 for behavioral disclosure. It correctly indicates a read-only operation ('Read'), but doesn't mention other traits like error handling, authentication needs, or rate limits. The presence of an output schema partially compensates.
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 with no wasted words. It immediately conveys the purpose and usage pattern.
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 tool with two parameters and an output schema, the description covers the essential information. It could mention that the output is a label object, but the output schema provides that detail, making the description sufficiently 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?
Schema description coverage is 0%, so the description must add meaning. It clarifies that either label_id or slug should be provided, which goes beyond the schema's type definitions. It does not specify behavior if both are provided, but the guidance is still useful.
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 'Read' and the resource 'a single label', and distinguishes it from sibling tools like create_label, delete_label, update_label, and list_labels by specifying its unique purpose of reading one label by identifier.
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 clear guidance on when to use this tool: to read a single label when you have its id or slug. While it doesn't explicitly mention when not to use it or alternatives, the context of sibling tools like list_labels implies the boundary.
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's 'Read' implies a safe, idempotent operation. However, it lacks disclosure on behavior when both parameters are provided, neither, or when the tag is not found. The output schema may compensate, but the description itself is 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?
Two concise sentences, front-loaded with the core action and parameter usage. No superfluous 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 the tool's simplicity, the description covers the main purpose and parameter semantics. The presence of an output schema reduces the need to explain return values. Missing details on error handling and mutual exclusivity prevent a perfect score.
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 0%, so the description must compensate. It explains that tag_id and slug are alternative identifiers for the tag, which adds essential meaning beyond the schema's type information.
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 'Read' and the resource 'a single tag', and specifies the identification methods (id or slug). This distinguishes it from sibling tools like list_tags or create_tag.
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 using either tag_id or slug, implying these are the two ways to specify the tag. However, it does not explicitly state when to use this tool versus alternatives like list_tags, nor does it discuss parameter priority or mutual exclusivity.
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?
The description clearly communicates the key behavioral trait of being read-only, which is critical for correct invocation. Without annotations, this fills a necessary gap. It does not discuss pagination or defaults, but these are covered by the schema.
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 (two sentences) and front-loaded with the primary action. Every word adds value, with 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?
Given the presence of an output schema and full parameter documentation, the description covers the essential purpose and constraint. It could optionally mention the return format, but the existing information is sufficient for correct use.
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 parameter details. The description adds no further semantics beyond what the schema provides, which is adequate.
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 ('List') and the resource ('users') with specific scope ('authors/staff'). This is sufficient to distinguish from sibling list tools which target different entities (e.g., list_members, list_posts).
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 notes that the tool is read-only and that the API forbids write operations, which guides the agent on appropriate use. However, it does not mention when to prefer this over other list tools or state any exclusions.
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; description states it fetches public page and stylesheets, implying a safe read operation. Lacks details on error handling or authentication, but adequate for a 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 purpose, no redundant words. Every phrase adds value: purpose, method, and usage guidance.
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 the tool's simplicity, the description covers the essential aspects: what it does, how to invoke (path vs blog_url), and when to use (before restyling). Output schema exists, so return values don't need elaboration.
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% (baseline 3). Description adds value by explaining why 'path' matters (different templates) and gives examples ('/', '/my-post/'), aiding correct usage 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 tool 'inspects a live Ghost page and returns its markup and CSS' with a specific verb and resource. It distinguishes itself from siblings like 'preview_theme' or 'download_theme' by focusing on fetching rendered page structure for styling.
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 advises passing the correct path because homepage and posts use different templates, implying use before restyling. No explicit exclusions or alternatives, but context is clear.
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 carries full burden. It discloses that member is created as free, labels are created if new, subscribing to newsletters, and that no email is sent. It does not mention auth requirements or side effects, but is fairly transparent for a create 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?
The description is concise (two sentences plus a bullet-like list) and front-loaded. Every sentence provides essential information without 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?
Given 5 parameters (1 required) and the existence of an output schema (which explains return values), the description is complete enough. It covers key aspects like required field, optional parameters, and side effects (no email sent).
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%, but the description adds value beyond the schema by explaining that labels are given as names (created if new) and that newsletter_ids need to be obtained from list_newsletters. This aids 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 verb 'Create' and the resource 'member from an email address'. It distinguishes from siblings like update_member and list_members by specifying the creation action.
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 explains that only email is required, and provides context for optional parameters (labels as names, newsletter_ids from list_newsletters). It also mentions no email is sent, guiding usage. However, it does not explicitly state when not to use or provide alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description fully discloses important behaviors: partial updates, archival/restoration via status, asynchronous email verification for sender_email, and allowed values for sender_reply_to. It leaves no ambiguity 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?
The description is concise and well-structured, using clear sentences and backtick formatting for values. It front-loads the core purpose and provides details in a logical order without wasted 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?
The description covers the main update behavior, archival, email verification, and reply_to options. With an output schema present, the lack of return value description is acceptable. However, it omits details on several parameters, making it slightly incomplete for full autonomy.
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 description adds meaning for key parameters (status, sender_email, sender_reply_to) but does not cover all nine parameters. Parameters like name, description, footer_content, and subscribe_on_signup are left undocumented. Given 0% schema coverage, the description should provide more comprehensive parameter 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 that the tool updates a newsletter by ID and changes only the passed fields. It distinguishes itself from siblings like create_newsletter and get_newsletter by focusing on updates.
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 explicit guidance on using status='archived' as a deletion mechanism and explains the sender_email verification flow. It also specifies valid values for sender_reply_to. However, it does not explicitly compare to other tools like create_newsletter, 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.
Behavior4/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden. It discloses which fields are editable and that pricing is immutable, and states the return value (updated offer summary). It doesn't cover authorization or error conditions, but the key behavioral constraint is communicated.
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?
Three sentences, no fluff. Purpose stated first, then constraint, then return. Every sentence adds value and is appropriately 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 an output schema exists, the description need not detail return format. It explains editable fields, fixed pricing, and return presence. Could add error cases or mention partial update behavior, but overall sufficient for a simple update 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?
Schema description coverage is 0%, so description must compensate. It summarizes the editable parameters (name, code, display_title, display_description) and explains that pricing is fixed. It doesn't detail individual parameter constraints, but provides context the schema lacks.
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 updates an offer by ID, listing the exact fields that can be modified (name, code, display title/description), distinguishing it from create_offer, get_offer, and list_offers.
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?
It implicitly indicates use for modifying existing offers and explicitly notes pricing terms are fixed, but does not contrast with alternatives like create_offer or mention prerequisites like offer existence.
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 must disclose behavior. It adds that the result includes rendered HTML and a preview_url, which are not schema properties. It implies a read-only operation. Could be improved by explicitly stating idempotency or permissions, but still informative.
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, no redundant information. Key details are front-loaded: what the tool does and how to use it.
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 read tool with an output schema, the description is complete. It covers the purpose, parameter usage, and key return fields (rendered HTML, preview_url). No missing critical behavior.
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 0%, so description compensates. It clarifies that page_id and slug are alternative identifiers and that one should be provided. This adds meaning beyond the schema, which only shows types and null defaults.
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 a single page by id or slug, including rendered HTML. The verb 'read' and resource 'page' are specific, and the method (by id or slug) distinguishes it from related tools like list_pages or create_page.
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 says to provide either page_id or slug, guiding parameter selection. It implies usage for reading a specific page. However, it does not explicitly state when not to use this tool or mention alternatives like list_pages for discovery.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden and excels: it discloses that the render uses sample content, stubs dynamic helpers, serves on localhost, stops previous previews, and makes old URLs invalid. All critical behavioral traits are covered.
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 concise, with three short paragraphs. The first sentence states the main action, followed by details on what is rendered and served, and a final behavioral note. No unnecessary words; every sentence earns its place.
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?
Despite an output schema existing, the description covers all necessary context: purpose, internal behavior, constraints (single preview, live URL expiry), and expected output (URL). It is fully complete for a single-parameter preview 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 only parameter, theme_path, is described in the schema as 'Path to the theme directory to preview.' The description does not add further detail (e.g., format, validation). Since schema coverage is 100%, baseline is 3, and no extra value is provided.
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: 'Render a Ghost theme locally and serve it for preview in a browser.' It specifies building static renders of home, post, and page templates, differentiating it from sibling tools like activate_theme or upload_theme.
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?
Provides explicit guidance on when to use: 'before activating the theme on the live site.' Also notes the single-preview behavior and advises handing the user the most recent URL. However, it does not explicitly exclude alternative scenarios or other tools.
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, but the description discloses partial update behavior and the retirement workaround. It does not mention authorization or rate limits, but covers key mutation aspects.
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?
Three short sentences, front-loaded with the core purpose. No unnecessary words; every sentence adds value.
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?
Output schema exists so return details are not needed. The description covers partial update, retirement workaround, and the general usage pattern adequately for the 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?
The description explains that any passed field is updated, but with 11 parameters and 0% schema coverage, it does not provide individual parameter details. The names are self-explanatory but no additional context given.
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 'Update a tier by id' and specifies that only passed fields are changed. It distinguishes from create_tier and mentions the return value.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states that partial updates are done by passing only the fields to change, and provides guidance on how to retire a tier (active=False) since there is no delete operation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility and does an excellent job disclosing behavioral traits: SSRF guard restrictions, source limitations (public http(s) only, rejects private/localhost and oversized responses), and the upload-to-Ghost hosting behavior. No contradictions.
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 consists of two focused sentences: the first states the core action, and the second adds essential constraints. It is front-loaded and contains no extraneous information.
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 the tool's simplicity, an output schema exists (returning the URL), so the description does not need to cover return values. It fully covers fetching, constraints, and hosting behavior, making it complete for an agent to select and invoke the tool correctly.
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 baseline is 3. The description adds no additional meaning beyond the schema for 'source_url' and does not mention the 'purpose' parameter. Thus, it provides no extra value over the input 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: 'Fetch a public image by URL and re-upload it to the blog, returning the URL.' The verb 'fetch' and 're-upload' combined with the resource 'image' make the purpose unambiguous. It distinguishes itself from sibling tools like 'upload_image' by explicitly mentioning fetching from a URL.
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 clear context on when to use the tool: when you have a public image URL and want to host it on the blog. It also lists constraints (SSRF guard, public http(s) only, no private/localhost, oversized responses refused). However, it does not explicitly state when not to use it or mention alternatives like 'upload_image' for local files.
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 carries full burden. It discloses that the tool creates a page (mutation), defaults to draft, and returns a preview_url for reviewing drafts. While it doesn't mention auth requirements or destructive behavior, for a creation tool this is sufficient.
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 four sentences with no redundant words. It front-loads the primary action and quickly provides essential details about status behavior, page characteristics, and return values.
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 the tool has 7 parameters (1 required) and an output schema, the description is complete. It explains the default draft, how to publish, the nature of pages, and the return summary including preview_url. The output schema covers return structure, so additional description is unnecessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the description adds meaning to key parameters: it explains the default for status, that pages are standalone (so no tags/feed), and that meta_title/meta_description set search-snippet metadata. This compensates fully for the lack of 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?
The description clearly states 'Create a page from HTML content' and distinguishes pages from posts by noting they are 'standalone (about, contact, …) with no tags or feed placement.' This provides a specific verb+resource and differentiates from sibling tools like create_post.
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 explains the default draft status and how to publish immediately by passing 'status="published"'. It also clarifies that pages lack tags/feed placement, guiding when to use this tool versus create_post. However, it does not explicitly state when not to use it or list alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but the description fully covers behavioral traits: it downloads, appends or replaces CSS, re-uploads, does not activate, and if the theme is active, CSS changes take effect immediately. It also mentions re-validation and error/warning returns.
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 front-loaded with the core action and then provides necessary details. It is slightly longer than minimal but every sentence serves a purpose, with no fluff.
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 the siblings and no output schema description, this description is thorough: it covers the file, modes, side effects, and validation. It fully equips the agent to use the tool 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?
Schema coverage is 100%, but the description adds value by explaining default append vs replace, the file path, and that 'name' is available via list_themes. It clarifies behavior 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 it restyles an installed theme by editing its stylesheet and re-uploading it. It distinguishes from siblings like create_theme, upload_theme, and download_theme by specifying 'iterate a theme already on the blog without regenerating it'.
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 gives clear context for when to use this tool (to modify CSS of an installed theme) and warns about live changes if the theme is active. However, it does not explicitly name alternatives or state 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.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description discloses key behaviors: partial update (only passed fields change), special handling of 'status' (publish/unpublish), and that empty 'html' leaves the body unchanged. It also mentions the return value (updated page summary).
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 concise (3 sentences) and front-loaded with the core action. Every sentence adds value without repetition or unnecessary detail.
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 8 parameters, 0% schema coverage, and no annotations, the description covers the critical behaviors (partial update, status/html handling). It doesn't explain error handling or prerequisites, but the presence of an output schema likely covers return values. Slightly more detail on other parameters would improve 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?
Despite 0% schema coverage, the description adds meaning to 'html' and 'status' parameters, explaining their special behaviors. It also clarifies the partial update model. However, other parameters (e.g., title, excerpt) are not explicitly described, but their names are self-explanatory.
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 'Update' and the resource 'existing page by id'. It distinguishes from siblings like 'create_page' and 'delete_page' by focusing on modification of an existing page.
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?
Provides specific guidance on using 'status' to publish/unpublish and the behavior of empty 'html'. While it doesn't explicitly state when not to use this tool, the partial update semantics and examples imply its appropriate use case.
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 clearly discloses that this tool changes what visitors see and is the go-live step. It does not mention permissions or rate limits, but it sufficiently describes the behavioral impact for a simple activation 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 paragraph with three sentences, front-loaded with the main action. Every sentence adds value with no unnecessary text.
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 the simple one-parameter tool with an output schema, the description is complete: it explains purpose, usage guidelines, and provides a cross-reference. The output schema covers return values, so no further detail 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?
Schema coverage is 100% (one required parameter 'name' is described). The description adds a helpful cross-reference to list_themes, aiding discoverability. Beyond that, it does not add syntax or format details, but the baseline of 3 is elevated due to the useful reference.
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 'Activate an installed theme, making it the LIVE theme. Changes the site.' This provides a specific verb and resource, and distinguishes it from sibling tools like upload_theme or preview_theme by emphasizing the go-live step.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says 'Call it ONLY on the user's explicit instruction to activate a specific theme -- never as an automatic follow-on...' and explains that upload installs inactive, so activation is a separate deliberate step. This provides clear when-to-use and when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Despite no annotations, the description fully discloses behavior: fetches page and CSS, reads navigation menus, refuses private/localhost hosts, and clarifies which links are kept out of suggested menus. No contradictions.
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?
Concise yet comprehensive; every sentence adds value. Front-loaded purpose, then context, then details and warnings. No fluff.
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 the presence of an output schema, the description covers all necessary context: input constraints (public HTTP), behavior (fetching, reading), and output expectations (brand match, navigation structure). Includes practical guidance for handling membership links.
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 reiterates the schema's parameter descriptions (site_url, path) but does not add substantial new semantic information 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 it extracts brand tokens from a public site, specifically as step one of theming a blog. It distinguishes from siblings like update_branding or restyle_theme by positioning as the initial analysis step.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says when to use it (first step of theming), where not to use (private/localhost), and provides guidance on navigation handling including a reference to update_navigation for writing menus. Gives clear alternative actions for membership links.
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 that the action is outward-facing, irreversible, sends real email, and explains scheduling behavior and the effect of an archived/unknown slug. Strong behavioral context, though could detail error handling or idempotency.
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 paragraphs with front-loaded key info (publish+email, real email warning). Every sentence adds value; no redundancy. Highly 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 4 parameters, no annotations, and presence of output schema, the description covers purpose, usage guidelines, behavioral impacts, parameter details, and alternatives. It is complete for an agent to invoke 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?
Schema coverage is 100%, so baseline is 3. The description adds value by explaining scheduled_at (schedule vs now), email_segment (NQL filter options), and newsletter_slug (source and archived/unknown behavior), going 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?
The description clearly states the tool publishes a post and emails it to newsletter subscribers, distinguishing it from update_post which publishes without emailing. The verb 'publish' and resource 'post' are specific.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states to call only on explicit user instruction to send, and provides an alternative (update_post(status='published')) for publishing without emailing. This gives clear when-to-use and when-not-to-use guidance.
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, but the description implies a read-only check without side effects. It does not explicitly state whether it's idempotent or non-destructive, but the nature of the tool (calculating a ratio) makes it clear. A higher score would require explicit mention of safety or permissions.
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 (two sentences) yet packed with information. The first sentence states the core purpose, and the second provides usage guidance and examples. No wasted words.
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 the tool's simplicity (2 parameters, clear purpose) and the existence of an output schema (not provided but noted), the description is complete. It tells the agent what the tool does, when to use it, and what inputs to provide, without needing to explain return values.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description adds meaning beyond the schema by specifying accepted color formats (hex with example, rgb()/rgba()) and giving real-world context (foreground as text, background as accent). This helps the agent understand parameter roles and valid inputs beyond the schema's minimal 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?
The description uses a specific verb ('Check') and resource ('WCAG contrast ratio'), and explicitly states the context ('before shipping a theme'). It clearly distinguishes from sibling tools like extract_brand or restyle_theme by focusing on contrast validation.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives explicit when-to-use guidance: 'Guards against unreadable text-on-accent' and provides concrete examples (button text vs background, body text vs page background). It also advises to use it in conjunction with extract_brand, offering a clear workflow.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully covers behavioral traits: it returns the created newsletter's summary, explains the opt_in_existing behavior, and notes that setting a custom sender_email requires an additional update step due to email verification. No contradictions.
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 concise, with each sentence adding unique value. It is well-structured and front-loaded with the primary 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?
For a 6-parameter tool with an output schema, the description covers the key complexities (required vs optional, special parameter values, return type). Minor gaps exist for some optional parameters, but overall it is complete enough for most use cases.
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 0%, so the description adds crucial semantics for 'sender_reply_to' (two possible values), 'opt_in_existing' (subscription behavior), and the 'sender_email' workflow. However, it does not explain 'description', 'sender_name', or 'subscribe_on_signup', leaving some parameters under-specified.
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 begins with a specific verb+resource ('Create a newsletter'), clearly distinguishing it from update_newsletter and other create tools. The purpose is immediately clear.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states that only 'name' is required, explains the values for 'sender_reply_to', and provides guidance on when to use 'update_newsletter' for custom 'sender_email'. No sibling tool ambiguity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description fully discloses behavioral traits: the menu is completely replaced, extra keys are ignored, URLs should be site-relative, and membership actions should not be included. This provides essential 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.
Conciseness4/5
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured and front-loaded, with clear sections. It is slightly verbose but every sentence adds value. It could be trimmed slightly without losing clarity, but overall it is effective.
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 the presence of an output schema (not shown but mentioned), the description is complete. It covers purpose, usage, parameter details, behavioral traits, and restrictions. No gaps are apparent.
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?
Although schema coverage is 100%, the description adds meaning beyond the schema by explaining the structure of menu items, the replacement behavior, and that passing null leaves the other menu unchanged. It also clarifies that extra keys are ignored.
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's purpose: setting the blog's navigation menus (primary header and secondary/footer). It uses specific verbs and resources, distinguishing it from sibling tools like update_site_settings or others that deal with different aspects.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly advises when to use (to set navigation menus) and when not to (membership actions should be in theme as Ghost Portal buttons). It also recommends confirming with user before calling, and strongly implies that this tool replaces menus entirely rather than appending.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Behavior5/5
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It thoroughly discloses behaviors: writes to disk, auto-injects stylesheet/ghost_head/foot, rejects certain Handlebars constructs, injects {{!< default}} if missing, and requires {{{body}}} in default_template. It also explains how styles interact with the brand accent color.
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 quite long but well-structured: a brief summary followed by detailed sections separated by blank lines. It is front-loaded with the core action. However, some sentences are lengthy and could be trimmed slightly for better readability.
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 the tool's complexity (7 parameters, output schema exists), the description is extremely complete. It covers prerequisites (helper subset), conventions (width, style injection), rejected constructs, and post-usage steps. No gaps remain.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Parameters5/5
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so baseline is 3, but the description adds significant value. It explains the styles parameter with accent color and width conventions, describes template parameters with injection rules and rejected elements, and elaborates on the default_template requirement for {{{body}}}.
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 starts with a clear one-sentence summary stating it generates a complete, valid, previewable Ghost theme on disk. It then details what files are written (layout, templates, CSS, package.json). It distinguishes from sibling tools like preview_theme and upload_theme by suggesting them as next steps.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Usage Guidelines5/5
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly tells when to use the tool (to generate a theme) and provides clear guidance on what Handlebars helpers are allowed vs. rejected. It suggests a workflow: generate, then preview_theme, then upload_theme. It also explains the width convention and how to handle layouts.
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:

[![ghost-mcp MCP server](https://glama.ai/mcp/servers/stemcreations/ghost-mcp/badges/card.svg)](https://glama.ai/mcp/servers/stemcreations/ghost-mcp)

Score Badge

Copy to your README.md:

[![ghost-mcp MCP server](https://glama.ai/mcp/servers/stemcreations/ghost-mcp/badges/score.svg)](https://glama.ai/mcp/servers/stemcreations/ghost-mcp)

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/stemcreations/ghost-mcp'

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