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

Annotations already declare readOnly, openWorld and idempotent, so the safety profile is covered. The description adds substantial non-obvious behavior: exact status taxonomy, that 'not_found'/'ambiguous' mean unconfirmed rather than fake, that corrections are returned inline, and a hard 50-reference cap. It does not mention rate limits, latency, or authentication, keeping it from a 5.

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?

Front-loaded with the core action and databases, then input formats, then the status taxonomy, then the cap. Every sentence carries information, though the status list is dense and slightly repetitive in the sentence re-explaining likely_fabricated/not_found/ambiguous/retracted.

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-input, open-world verification tool with an output schema, the description covers the input formats, the exact output statuses, the semantic meaning of each status, and the batch limit. Nothing material an agent needs to call it correctly is missing.

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% and there is one parameter, so the schema already documents the single 'references' input. The description still adds meaning by enumerating concrete accepted formats (APA, Vancouver, numbered, mixed, BibTeX, RIS, CSL-JSON, DOI-per-line) beyond the schema's generic phrasing, which genuinely helps the agent format input correctly.

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 reference in a list) against three named databases, and enumerates the six possible statuses so the agent knows exactly what the tool produces. Distinct from siblings like check_retractions (retraction-only) and format_citations (style-only) by covering existence and detail correctness across all statuses.

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?

Clearly scopes the input to 'lists written by a person or generated by an AI model' and enumerates accepted input formats, and the 50-reference cap implicitly tells the agent when to split work. It does not explicitly name alternatives (e.g. use check_retractions when only retraction status is needed), so it stops short of a 5.

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