cite-gate

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

With no annotations, the description carries the full burden and does disclose useful operational behavior: the 3000-character prose limit per call and the local-server fallback. It does not describe permissions/auth needs or what a failing check produces, so it falls short of full disclosure for a tool with no output schema.

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: the first front-loads the core verification behavior, the second carries the operational limit and fallback. No filler, and the most important information comes first.

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 nested-object tool with no output schema and no annotations, the description should also indicate the shape of the result (what a citation failure looks like). It explains inputs and limits well but is silent on return values and error behavior, leaving a real gap given there is no output schema to fall back on.

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%, but the claims parameter is documented only as a cryptic stringified JSON template. The description compensates by clarifying semantics: quotes must match word for word, numbers and names in prose must appear in quotes, and prose must not copy — constraints an agent needs to build valid claims/sources input.

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 gives a specific verb ("Check") and enumerates three concrete verification criteria: verbatim quote backing, numbers/names appearing in quotes, and prose retelling rather than copying. It is very clear what the tool does, but it never names or distinguishes itself from the sibling check_numbers, which overlaps with the numbers/names criterion.

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?

It states the context of use (scripts with sources) and provides an explicit alternative path: the 3000-character hosted limit with an instruction to run the local server for longer scripts. It lacks any guidance on how this differs from check_numbers, so a sibling-selection rule is missing.

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 are provided, so the description carries the full behavioral burden. It omits critical behavior: what counts as a match (exact substring vs. numeric normalization, e.g. '1,000' vs '1000'), case/format handling, ordering, and what the result looks like.

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 with no filler; the qualifying clause 'that do not appear in any of the given quotes' is placed after the core operation, so nothing is wasted.

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 annotations, no output schema, and 0% schema description coverage across two required parameters, the description would need to carry matching semantics and result shape. It states only the high-level operation, leaving the agent to guess how the check is performed.

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 the description must compensate; it does partially by mapping 'a piece of prose' to text and 'given quotes' to quotes. However it adds no format detail (e.g. whether quotes must be verbatim excerpts), leaving real ambiguity about how inputs are consumed.

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?

Specific verb+resource: lists numbers in prose that are absent from the supplied quotes. The set-complement framing makes the operation clear, though it never explicitly distinguishes itself from the sibling check_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 implies the use case (verifying that numbers in a text are backed by quotes) but offers no explicit when-to-use, prerequisites, or guidance on choosing it over check_citations. Usage is inferable rather than stated.

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