citation-verifier

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

With no annotations, the description must disclose behavioral traits. It only states what is extracted, but doesn't mention whether the tool is read-only, if it modifies data, return format, error handling, or any limitations. Minimal disclosure beyond the tool's name.

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 action and resources. It is efficient with 13 words, though it could be slightly more structured with separate items.

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 a single parameter and no output schema, the description covers the basic extraction purpose. However, it lacks details on output format, edge cases (e.g., no citations found), and behavior under different inputs, making it minimally 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?

Only one parameter 'text' exists with 0% schema description coverage. The description mentions 'from text' implicitly linking the parameter, but does not explain format constraints, max length, or encoding expectations. Basic clarification but not detailed.

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 extracts multiple specific types of references (URLs, paper refs, DOIs, arXiv ids, statistics) from text. It uses a specific verb 'Extract' and lists resources, distinguishing it from sibling tools like probe_url and verify_citations.

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 vs alternatives. There's no mention of prerequisites, input text requirements, or scenarios where extraction is appropriate.

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 the tool checks reachability and finds the final destination (implying redirect following). However, it lacks details on what 'probe' entails (e.g., request method, timeouts, error handling) and no annotations provide additional safety info.

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 clear sentence of 10 words, front-loaded with key information. Every word serves the 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?

Given the tool has no output schema, the description should at least hint at return values (e.g., HTTP status, final URL) or error conditions. It does not, leaving the agent uncertain about what to expect 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?

The single parameter 'url' has no schema description and the tool description does not add any meaning, such as expected format (e.g., need protocol) or constraints. With 0% schema coverage, the description fails to compensate.

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 probes a URL for reachability and final destination. The verb 'probe' is specific, and it distinguishes from siblings (extract_citations, verify_citations) which deal with citations.

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

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

The description provides no guidance on when to use this tool versus alternatives. It does not mention when not to use it, nor does it provide context about prerequisites or competing tools.

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

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

No annotations exist, so the description bears full burden. It mentions extracting and probing, but does not disclose how probing works (e.g., network requests, timeouts) or what the trust score entails (e.g., scale, criteria). Side effects are unclear.

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 brief (single sentence), but it sacrifices clarity for brevity. It reads like a tagline rather than a functional description.

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 sibling tools and lack of output schema, the description is insufficient. It does not explain what the trust score means, how to interpret results, or when to prefer this tool over extract_citations or probe_url.

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

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

Schema coverage is 0%, so description must compensate. It implicitly ties 'text' to extraction and 'probe_urls' (default true) to the probing behavior, but does not explicitly describe either parameter. The boolean's effect is only hinted.

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 extracts URLs, probes them, and returns a trust score. It distinguishes from sibling tools (extract_citations and probe_url) by combining both actions and adding a score, though not explicitly.

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 the siblings (extract_citations or probe_url). The description does not mention any context or prerequisites.

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