campus_research_verify_quotes

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so safety is covered. The description adds real behavioral context beyond them: the return payload ('per-quote status and allExcerptsLocated') and a precise semantic boundary (location only, not claim support), plus the index_pdf dependency for documentId/analysisId.

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 action is front-loaded in the first sentence, and every following sentence carries distinct information (inputs, returns, usage constraint, scope limit). Dense but not padded; only the stacked clauses make it slightly heavy going.

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 5-required-param tool with 0% schema description coverage and no output schema, the definition covers inputs, provenance, return fields, and the key semantic limitation. The main residual gap is the absent contrast with the singular verify_quote sibling, which an agent selecting between them would need.

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 0%, so the description must carry the load and largely does: it maps documentId/analysisId to their origin in index_pdf, identifies url and expectedSha256 as the original URL and hash, and clarifies that citations are page/excerpt pairs. It omits the excerpt length bounds and per-field format expectations, so it is not fully compensating.

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 (check/verify) and resource (every literal quotation planned for one answer), with batch scope made explicit via 'one cached-PDF call (up to 8)'. The singularity sibling campus_research_verify_quote is never named or contrasted, so the agent must infer the batch-vs-single distinction from the 'up to 8' phrasing alone.

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 gives downstream usage rules ('omit any rejected or inconclusive quote', 'never expand a verified excerpt with unverified words') and scopes the tool ('confirms text location only, not whether a quote supports a claim'). But it never states when to pick this over the near-identical campus_research_verify_quote, verify_evidence, or verify_citation siblings, which is the harder routing decision here.

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