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

Annotations already cover safety (readOnly, idempotent, openWorld), so the description's job is to add match behavior — and it does: names return ranked candidates with ambiguity risk, identifiers match exactly. It stops short of describing pagination or result ordering beyond ranking, but the added ambiguity warning is genuinely useful.

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 purpose, then value, then usage guidance; every sentence earns its place. It is dense and slightly long, but not padded — no restatement of the title or name.

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 needn't enumerate returns, yet it still previews the profile shape and the literatureQuery handoff. Together with the routing advice, an agent has everything needed to call it correctly.

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 schema already lists accepted identifier formats, so baseline is 3. The description adds match semantics per query type (ranked candidate list for names vs exact for identifiers) that the schema does not convey, pushing it slightly above baseline.

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 physicist profiles in INSPIRE-HEP) and enumerates the five accepted lookup keys. It is clearly distinguishable from siblings like cern_inspire_search_literature and cern_inspire_get_citation_summary, which it names.

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?

Explicitly routes the agent: confirm the person via positions/categories before passing a bai or recid to cern_inspire_get_citation_summary, and notes the literatureQuery feeds cern_inspire_search_literature. It also warns that a bare surname can match tens of thousands of profiles and that a less-cited namesake can rank first, which is real when-not-to-trust guidance.

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