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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so safety needs little restating, but the description adds no behavior beyond them. It says nothing about pagination via cursor, the cached_if_fresh vs fresh tradeoff, the summary/full response-size behavior, or any quota/rate constraint despite a quota sibling existing. The only addition is a guide URI, which defers rather than discloses.

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 compact fragments, with the core purpose front-loaded and the sibling routing immediately after the example. Nothing is padded, though the guide URI is a weak use of the final slot and "ordinary records" spends words without adding precision.

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?

This is a broad, high-complexity search surface — 7 parameters, 14 entity types, 20 filter fields gated per entity, plus an output schema — and the description covers only the query/entity/filters triad. For a tool with an output schema the return shape need not be explained, but the entity vocabulary, pagination, and freshness/output semantics are left entirely to the schema.

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 only 14%, so the description carries real burden, yet it explains a single invocation shape: {"entity":"gene","query":"BRCA1","filters":{"species":9606}}. It never touches limit, cursor, output, or freshness, and does not mention that valid filter keys are constrained per entity by the schema's conditional blocks — a non-obvious rule the one example only hints at.

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?

"Find ordinary records with entity filters" gives a verb and a resource, and the two exclusion sentences distinguish it from literature_search and trial_search. However, "ordinary records" is vague: the entity enum contains 14 domains (gene, variant, drug, gwas, patent...), and the description never characterizes the record corpus it actually searches.

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?

It explicitly routes two adjacent needs away — papers to literature_search, trials to trial_search — which is exactly the sibling differentiation an agent needs. It stops short of positive guidance (when to choose this over get, query_source, relate, or research), so it is clear context without full alternative coverage.

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