library

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

Annotations already indicate readOnlyHint=true, so description's mention of getting a citation is consistent. No additional behavioral traits (e.g., network fetch, rate limits) are disclosed, but it's acceptable for a simple read operation.

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

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

Two sentences, no fluff. Front-loaded with purpose and supported styles. Every sentence adds value.

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

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

Tool is simple with well-documented parameters. Missing output format description (e.g., returns string), but overall sufficient for selection and invocation. Annotations cover safety.

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

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

Schema coverage is 100% with descriptions for both slug and format. Description reinforces the format enum values but adds no new meaning beyond what schema provides. Baseline 3 is appropriate.

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

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

Description clearly states the tool gets a formatted citation for a specific article (ADHD in Children) and lists supported styles. It distinguishes from siblings like get_article (content retrieval) and list_articles/search_articles.

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

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

The description implies usage for citation formatting and lists supported styles, but does not explicitly state when not to use it or provide alternatives. However, sibling tool names clarify the context.

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

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

Annotations already declare readOnlyHint=true, so the description's additional listing of specific return fields (title, body, author, etc.) adds useful behavioral context. It does not contradict annotations and provides clarity on what the tool exposes.

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

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

A single, front-loaded sentence that directly states the action, resource, identifier, and return fields. Every word contributes value; no wasted text.

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

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

For a simple fetch tool with one required parameter and no output schema, the description adequately covers what the tool does and returns. It could include optional hints about response format but is sufficiently complete for an agent to use correctly.

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

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

The schema covers the sole parameter 'slug' with a description ('Article slug.'). The tool description does not add any extra meaning or usage guidance for this parameter beyond what the schema provides.

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

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

The description clearly specifies the action ('Fetch a single article'), the resource ('from ADHD in Children'), the unique identifier ('by slug'), and lists the returned fields. This distinguishes it from siblings like 'list_articles' or 'search_articles'.

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

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

The description implies usage when a specific slug is known but does not explicitly state when to use this tool versus alternatives (e.g., 'search_articles') or when not to use it (e.g., if needing citations). No usage context or exclusions are provided.

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

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

Annotations already provide readOnlyHint=true, indicating a safe read operation. The description adds context that it returns a crisis resource payload, which is beyond what annotations convey. No contradiction.

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

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

The description is extremely concise with two sentences, no redundancies, and front-loads the core action: 'Return the canonical payload.' Every part earns its place.

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

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

Given no parameters, no output schema, and a simple result, the description fully informs the agent of what the tool does and when to call it. No information gaps.

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

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

No parameters exist, so schema coverage is 100%. The description adds no param info, which is appropriate since there are none. Baseline of 4 applies as no compensation needed.

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

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

The description clearly states the tool returns the canonical 988/911/Crisis Text Line payload. It specifies the exact resource (crisis resources) and indicates when to use it (self-harm/imminent danger). Distinguishes from article-related sibling tools effectively.

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

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

Explicitly guides when to use: 'Surface this immediately whenever the user signals self-harm or imminent danger.' This is clear, unambiguous, and leaves no doubt about the appropriate invocation context.

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

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

The annotations already declare readOnlyHint=true, so the safety profile is known. The description adds specific behavioral context by listing the content the tool returns (tagline, audience, focus, etc.), which conveys it is a read-only metadata retrieval. No contradiction with annotations.

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

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

The description is a single, front-loaded sentence that efficiently lists the key information types provided. Every phrase adds value, with no redundant or extraneous content.

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

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

The tool has no parameters, no output schema, and low complexity. The description lists the data points returned (tagline, audience, etc.) but does not specify if the output is structured or whether all fields are always present. A small addition about the return format would improve completeness, but the current description is minimally adequate for such a simple tool.

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

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

There are zero parameters and schema coverage is 100%, so the baseline is 4. The description does not need to add parameter meaning. It correctly focuses on what the tool returns, which is sufficient given no inputs.

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

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

The description clearly states the tool provides identity and links for a specific microsite (ADHD in Children), listing specific attributes like tagline, audience, and URLs. The verb 'get' and resource 'microsite info' align with the name and title. While distinct from sibling tools that focus on articles, the description does not explicitly differentiate, but the single-resource scope makes purpose clear.

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

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

The description implies this tool is for retrieving metadata about a specific microsite, not for articles or content. However, there is no explicit guidance on when to use it versus alternatives, nor any exclusion or prerequisite information. The context from sibling names suggests differentiation, but the description lacks direct usage context.

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

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

Annotations already declare readOnlyHint=true, so description adds minimal behavioral context beyond listing returned fields. No mention of performance, rate limits, or other traits. No contradiction with annotations.

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

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

Single sentence with all essential information: paginated list, source, returned fields. Front-loaded and concise with no redundant words.

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

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

Given no output schema, description lists return fields but omits details like default values, ordering, or response structure. Adequate for basic use but could be more complete for pagination behavior.

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

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

Schema coverage is 100%, both parameters (page, limit) are well-described in the schema. The description does not add additional meaning beyond what the schema already provides.

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

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

The description clearly states it is a 'paginated list of articles' from a specific source ('ADHD in Children') and lists the returned fields (title, slug, summary, URL). This distinguishes it from siblings like get_article (single article) and search_articles (search).

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

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

The description implies usage for browsing articles but does not explicitly state when to use this tool versus alternatives (e.g., search_articles for specific queries, get_article for a single article). No exclusions or context provided.

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

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

Annotations already mark the tool as readOnlyHint=true, indicating a safe read operation. The description adds context by specifying the corpus searched and the return fields. No contradictions, but it lacks details on pagination or data freshness.

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

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

The description is a single, well-structured sentence that immediately conveys the action, target, and output. Every clause serves a purpose.

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

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

For a simple search tool with three well-described parameters and annotated readOnlyHint, the description provides enough context about what is searched and what is returned. No output schema exists, but the return fields are explicitly listed.

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

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

The input schema covers 100% of parameters with descriptions. The tool description adds no additional meaning beyond what the schema provides, so the baseline score of 3 is appropriate.

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

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

The description clearly states the tool searches an editorial corpus by query and returns specific fields (title, slug, summary, URL). This distinguishes it from sibling tools like list_articles (likely listing all) and get_article (retrieving one).

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

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

The description implies use for free-text search against a specific corpus, which contrasts with sibling tools that serve different purposes (citing, getting a single article, listing). However, it does not explicitly state when not to use this tool or provide alternatives.

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