citeguard

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

Without annotations, the description discloses key behaviors: extracts pairs, verifies sources, returns a score. It does not mention error handling or timeouts, but adequately covers the main workflow 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.

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

Single sentence, front-loaded with the verb 'audit', efficient and no wasted words. Every part contributes to understanding.

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

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

Given the single parameter and no output schema, the description explains the process and return value (report with integrity score). It could detail the report structure, but overall it's sufficient for the tool's complexity.

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

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

The schema describes the parameter as 'Document text (markdown or plain text)'. The description adds concrete details about what the document should contain (links, footnotes, DOIs, URLs), which provides semantic value beyond the schema.

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

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

The description clearly states the verb 'audit' and the resource 'citations in a document'. It specifies extraction of claim+source pairs (markdown links, footnotes, DOIs, bare URLs) and verification, distinguishing it from sibling tools like check_links and verify_claims.

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

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

No explicit guidance on when to use this tool versus siblings. The description is specific to citation auditing, but does not mention when not to use it or provide comparative context.

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

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

No annotations provided, so the description carries full burden. It discloses that the tool extracts URLs, checks liveness, and reports specific outcomes (dead links, redirects, archive.org). It does not mention potential network requests or rate limits, but for a liveness check this is reasonable. 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 sentence that is front-loaded with key information ('Liveness-only check (no LLM)') and contains no superfluous words. 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 the simple input (one text parameter), no output schema, and no annotations, the description adequately covers the tool's behavior and outputs. It specifies what it reports (dead links, redirects, archive.org), but could optionally mention the output format or any limitations (e.g., URL count).

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

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

The single parameter 'document' is fully described in the schema as 'Document text (markdown or plain text)'. The tool description adds value by stating it 'extracts all cited URLs', clarifying how the parameter is used beyond its type.

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 performs a 'liveness-only check' on cited URLs, extracts them from the document, and reports dead links, homepage redirects, and archive.org availability. This distinct purpose differentiates it from sibling tools like check_document and verify_claims.

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

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

The description explicitly notes it is a 'liveness-only check (no LLM)', guiding the agent to use it for link health verification rather than content analysis. However, it does not explicitly mention when not to use it or direct to alternatives, though the sibling context provides some inference.

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 description discloses that URLs are fetched and verdicts are returned, including 'could_not_fetch'. However, without annotations, it does not mention side effects, rate limits, or idempotency, leaving some behavioral aspects unspecified.

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, concise sentence that front-loads the core purpose and includes key details about verdicts and evidence spans.

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 and no annotations, the description adequately explains input, process, and output format. It covers the verdict list and evidence span, though the exact response structure could be more explicit.

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 already provides descriptions for all parameters (text, source, context), achieving high schema coverage. The tool description does not add additional meaning 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 states the tool verifies claim+source pairs and lists possible verdicts. It is specific about the verb and resource, but does not explicitly distinguish from sibling tools check_document and check_links.

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

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

No guidance is provided on when to use this tool versus alternatives. The description lacks context about prerequisites, limitations, or scenarios where siblings 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.