Citation Verification

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

No annotations are provided, so the description bears full responsibility. It discloses the three checks and the batch limit, but does not mention authentication needs, rate limits, or what happens on invalid input. The output format is not described, leaving the agent to infer success/failure states.

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 three sentences with no wasted words. It front-loads the core functionality, then provides usage guidance and constraints. Every sentence 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?

With no output schema and moderate complexity, the description lacks details about the return format (e.g., per-citation results, error handling). While it hints at a match_score, the overall output structure is missing, which is required for an agent to fully understand the tool's 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?

The input schema includes descriptions for the 'url' and 'claim' fields, but the tool description adds value by clarifying that DOIs can be passed directly and that up to 25 citations are allowed. It also explains that providing a claim yields a match_score, which is not in 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 tool verifies that cited URLs resolve, match the claim text, and are not retracted. It specifies the exact checks performed using verbs like 'verify', 'resolve', 'match', and 'aren't retracted'. This distinguishes it from siblings like fact_check and source_freshness by focusing on citation integrity.

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 mentions when to use the tool ('when an LLM produced inline citations and you want to confirm they're real and on-point') and provides input format guidance (DOIs or full URLs, up to 25 per call). No exclusions or alternatives are discussed, 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.

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

No annotations provided, so description must cover behavioral traits. It mentions return values (verdict, confidence, sources) and truncation behavior from schema. However, does not disclose potential latency, required permissions, or how authoritative sources are accessed. Adequate but missing details.

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 front-loading purpose and usage advice. No wasted words, efficient and clear.

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 tool with no output schema, description covers purpose, usage, and return format. Missing explanation of what happens with multiple claims or edge cases, but overall sufficient.

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 one parameter. Description adds meaning by specifying 'ideally one sentence' and noting truncation to 200 chars, which is helpful beyond the schema's description.

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?

Clearly states verb 'verify' and resource 'factual claim against authoritative sources', listing specific sources (Wikipedia, Wikidata, Crossref). Distinguishes from siblings by focusing on verification of claims, whereas cite_check and source_freshness likely handle citations and freshness.

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 says 'Use this when an agent is about to assert a fact it isn't 100% sure of, or when post-processing LLM output to flag possibly-hallucinated claims.' Provides clear context for when to use, though does not explicitly state when not to use or mention alternatives.

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?

With no annotations provided, the description carries the full burden. It discloses the returned data (last-modified, Wayback snapshot, 90-day flag) but omits details like rate limits, redirect behavior, or handling of inaccessible URLs.

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, directly stating purpose and use case with no extraneous information. It is front-loaded and efficient.

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 one-parameter tool with no output schema, the description adequately explains purpose, return values, and a usage scenario. Minor gaps like interpreting 'changed_recently' do not significantly detract.

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% for the single 'url' parameter. The description does not add meaning beyond the schema's 'URL to check' description, so 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 checks if a URL is live and how recently it was modified, listing specific return values (last-modified header, Wayback snapshot, changed_recently flag). It distinguishes itself from sibling tools by focusing on freshness and liveness.

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 recommends use for RAG hygiene to flag changed citations. While it doesn't mention when not to use or alternatives, the use case is clearly stated, providing adequate guidance.

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