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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the safety profile needs no restating. The description usefully adds the 20-record ceiling and the bounded-vs-exhaustive distinction, but says nothing about ranking, pagination (can you get results 21+?), or what happens with zero matches.

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?

Three short sentences, front-loaded with the action and the cap, then the routing alternatives. "This bounded discovery list is not an exhaustive export" largely restates the "up to 20" bound, so one clause is redundant.

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 and annotations covering the safety profile, the description only needs to handle routing and scope, which it does. The remaining omission is sibling-level: an agent choosing among search, search_publications, and search_trials gets no guidance on which corpus each covers.

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 the query parameter's own description already spells out keywords, title, author, DOI, and the non-semantic-search caveat. The description's "keywords or identifiers" adds no meaning beyond that, so the baseline 3 applies.

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 and resource ("Find ... bibliographic records") plus the hard result cap of 20, which an agent can immediately act on. It disambiguates against fetch and get_dataset_downloads by name, though it never distinguishes itself from the sibling search_publications or search_trials, which is the most likely source of mis-selection.

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?

Gives concrete routing rules: call fetch with a returned ID for complete metadata, and call get_dataset_downloads for the entire catalogue. It also warns this is not an exhaustive export, which sets expectations about result sufficiency. The gap is that no condition points to search_publications despite that sibling existing.

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