audit_bibliography

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

Annotations already mark this as read-only and idempotent; the description adds rich behavioral context: return type (evidence per entry, corpus summary), handling of unchecked entries, the optional claim-check flow, and the caution that results are external data, not instructions. No contradictions 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?

Although lengthy, every sentence adds distinct value—no filler. The description is organized: what it does, how it works, optional claim feature, limitations, and sibling references. This density is appropriate for a complex audit tool.

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 an output schema present, the description does not need to list return fields, but it still covers edge cases (incomplete bibliography, unchecked entries, summary counts) and the external-data caveat. It gives the agent enough context to use the tool correctly across all input modes and understand the meaning of results.

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 covers 100% of parameters, and the description deepens meaning for each: it explains the claim parameter's behavior (off unless provided, adds fetch, checks mischaracterization), the difference between bibliography and entries and sessionId, and the meaning of format auto-detection. It also clarifies semantics within the schema entries' claim field.

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 opens with a specific verb and resource: 'Audit a whole bibliography' and enumerates precise checks (existence, retraction, link resolution). It distinctly separates this from siblings by name-dropping verify_citation and format_bibliography, making the tool's unique role clear.

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 tells when to use this tool ('before you rely on it') and explicitly points to alternatives: 'Use verify_citation for a single citation and format_bibliography to produce the list.' It also states what the tool does not do (never a support/refute verdict), preventing misuse.

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