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

Annotations already establish read-only, idempotent, non-destructive, open-world behavior, so the description gets credit for adding operational context beyond that: a per-user daily search limit, the 'usually within seconds' latency, a cap of eight sources, and the explicit statement that no answer is written. It does not say what happens when the daily limit is hit, which keeps it below 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 capability, then the return shape, then the boundary against ask_cliniatlas and safety constraints. Two short paragraphs with no redundant or filler sentences.

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?

An output schema exists, so return-value explanation is optional, yet the description helpfully previews the source fields and latency. Rate limits and privacy constraints are covered. The only material gap is the undocumented 'locale' parameter, which an agent must infer from the schema alone.

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% for two parameters. The description implies the 'question' parameter is a clinical or research question, but adds no format, length, or content guidance beyond the schema's minLength/maxLength constraints, and never mentions the 'locale' parameter or its pattern at all. With low coverage the description needed to compensate and does not.

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 (live search) and concrete resources (PubMed, Europe PMC, clinical guidelines, EMA documents), and explicitly distinguishes itself from the sibling ask_cliniatlas by noting it does not write an answer. An agent can tell what this tool produces (up to eight sources with study type, evidence level, link) without opening the schema.

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 clear context (clinical or research question), names the alternative tool (ask_cliniatlas) for a full checked answer, and states the citation-by-number workflow plus a privacy constraint ('Do not include patient identifiers'). It does not clarify when to prefer this over other siblings like lookup_pubmed or search_evidence_library, so it falls short of a full 5.

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