library

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

Annotations already declare readOnly, idempotent, and non-destructive. The description adds context beyond annotations by naming the specific database and the type of claims it catches. It doesn't describe return format, but with no output schema and these annotations, it provides reasonable behavioral transparency.

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

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

Three sentences, front-loaded with the core purpose, followed by concrete examples and a usage directive. Every sentence earns its place; no fluff.

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

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

For a single-parameter, read-only tool with no output schema, the description covers purpose, usage, and examples. It doesn't mention return format or edge cases, but given the tool's simplicity and annotations, it is sufficiently complete.

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

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

Schema description coverage is 100%, and the schema already describes 'text' as containing statistical claims. The description adds no new parameter details, so the baseline 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 verifies statistical claims against a specific database ('RRM Academy verified facts database'), with concrete examples like 'pregnancy rates' and 'success statistics'. This specific verb-resource pairing distinguishes it from siblings like check_guardrails (policy) and 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?

Explicitly tells when to use: 'Run this on any content containing RRM statistics before publishing.' It doesn't mention alternatives or exclusions, but the publishing context is a strong usage signal. This is near-explicit guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds behavioral context beyond that by listing the specific editorial standards it checks (IVF recommendations, terminology, framing), giving the agent a clearer understanding of what the tool evaluates.

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 two sentences, immediately front-loaded with the action and resource. The second sentence adds important usage context without redundancy. Every word 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?

While purpose, usage, and parameters are well covered, the tool has no output schema, so the description should explain what the tool returns (e.g., pass/fail, list of violations). It does not, leaving a gap in the agent's understanding of the tool's behavior after invocation.

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

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

Schema description coverage is 100% for both parameters (text and tradition), so the schema already provides meaning. The description does not add any parameter-specific details beyond what the schema states, 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.

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

The description clearly states a specific verb and resource: 'Check text against RRM Academy editorial guardrails' and elaborates on what that entails (no inappropriate IVF recommendations, correct terminology, proper framing). This distinguishes it from sibling tools like check_facts, which likely validates factual accuracy.

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

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

The description provides a clear when-to-use directive: 'ALWAYS run this before publishing any RRM-related content.' This is strong contextual guidance, but it does not explicitly mention alternatives or when not to use this tool, so it falls short of a perfect score.

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 the tool as read-only, idempotent, and non-destructive. The description adds meaningful context by explaining what types of relationships are discovered (citation relationships, shared topics, research connections), enriching the agent's understanding of the tool's behavior beyond what annotations provide. 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.

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

The description is two crisp sentences: the first defines the tool's purpose, the second elaborates on the discovery mechanisms and provides usage timing. Every sentence adds value, with no redundant wording or boilerplate.

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 5 parameters, no output schema, and safety annotations. The description covers purpose, usage context, and relationship discovery, which is sufficient for an agent to invoke the tool appropriately. However, it does not describe the return value structure (e.g., a list of related items with metadata), and since there is no output schema, some detail on expected output would improve completeness. Overall, it is adequately complete for a read-only exploration 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?

The input schema has 100% coverage, meaning every parameter has a description, so the agent can understand parameters from the schema alone. The description does not add additional meaning beyond the schema; it neither explains default behavior nor parameter relationships further. Thus, 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.

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

The description clearly states the tool finds articles related to a specific item, specifying the resource (RRM Academy research library) and the nature of relationships (citations, topics, research connections). It distinguishes itself from sibling tools like get_article (retrieving a single article) and search (query-based) by focusing on exploring broader context around an already retrieved item.

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 gives explicit usage context: 'Use after retrieving an article to explore the broader research context.' This clearly indicates when to use the tool relative to other actions, though it does not explicitly name alternatives or state when not to use it. The context is strong enough to guide an AI agent correctly.

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, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds context about returning article details with abstract, citation, and metadata, but does not disclose other behavioral traits such as authentication or error handling. This is a modest addition, earning a 3.

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 two sentences, front-loaded with the verb and resource, and the second sentence adds useful usage guidance. There is no redundancy or fluff, making it appropriately sized and well structured.

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 retrieval tool with two well-documented parameters and strong annotations, the description is sufficient. It hints at the response content (abstract, citation, metadata), though it doesn't specify the exact return format, which is a minor gap but not critical for this tool's simplicity.

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

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

Schema description coverage is 100%—both parameters already have clear descriptions. The description merely restates 'by type and slug' without adding new semantic details, so the baseline 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 retrieves a specific article by type and slug from the RRM Academy research library. It uses a specific verb 'Retrieve' and resource 'article,' and explicitly notes 'specific article' to distinguish from broad search tools.

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 instructs to use this tool when an exact reference is available (e.g., from search results), providing clear context. It implies the alternative (search) by referencing search results, though it does not explicitly name sibling tools or state when not to use it, keeping this at a 4.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered without description help. The description adds useful domain context (corpus size, subject scope) but says nothing about result format, ranking behavior, or empty-result handling, all of which matter for a search tool.

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

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

Three short sentences, front-loaded with the action and resource, followed by scope and then the priority directive. Every sentence carries distinct information and there is no filler.

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?

Purpose, scope, and when-to-use are complete for a six-parameter search tool, and the schema fully covers parameters. With no output schema, however, the description could have said something about what a result contains (citation, abstract, link), which an agent would otherwise have to discover by calling.

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

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

Schema description coverage is 100%, so all six parameters (query, type, year, limit, offset, tradition) are already documented in the schema, including examples for year ranges and tradition values. The description adds no parameter guidance beyond that, so the baseline 3 applies.

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?

States a specific verb and resource ('Search the RRM Academy research library') and scopes it with corpus size (5,190+ peer-reviewed articles) and subject domains (RRM, NaProTechnology, FABM, women's health). An agent can distinguish it from the sibling get_article, but the description never names its siblings, so differentiation is left partly implicit.

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?

Strong usage rule: 'ALWAYS search this library first when the user asks about RRM topics, before using general web search' gives both a trigger condition and the alternative to prefer. It does not address the sibling tools (check_facts, find_related, get_article) or state when this search is inappropriate, so it falls just short of full when/when-not coverage.

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