paper

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered. The description's contribution is disclosing that the response bundles copies with licence and sharing flag plus a section list and abstract, which is useful content-level context. It stops short of noting pagination, truncation, or what happens when copies are unavailable.

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?

One short sentence with no filler, and the most important payload items are listed up front. It loses a point for being a bare fragment rather than a complete statement of what the tool does.

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, the description does carry the burden of describing return values, and it does so at a high level (metadata, copies, licence/sharing flag, sections, abstract). However, for a tool whose whole purpose is returning structured data, it omits any sense of structure, size, or edge-case 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?

Schema description coverage is 0% and the single work_id parameter is never mentioned in the description, so nothing is added beyond the schema. The parameter name is largely self-explanatory as a work identifier, which keeps this from being a real failure, but the definition provides no help on identifier format or provenance.

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 enumerates the resources returned (metadata, copies, sections, abstract) of 'a work', which implies a retrieval-by-work tool, but it is a noun phrase with no verb and never states that it fetches a single paper's record by ID. It does not distinguish itself from siblings like get_passage or get_table, which return other slices of the same work.

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?

There is no when-to-use guidance, no statement of prerequisites (does the work need to exist / be accessible?), and no routing to alternatives such as search_works for discovering a work_id. The agent must infer usage entirely from the name and the required parameter.

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