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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds meaningful context beyond that: the exact fields each compact record contains and the default ordering rule (relevance with a query, evidence strength without one). It does not mention pagination limits or result caps, which a 12-param search tool would benefit from.

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?

Two dense sentences with no filler; the retrieval purpose is front-loaded and the return-shape and sort behavior follow in a logical order.

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?

For a 12-param filter tool with no output schema, describing the returned record fields is exactly the right compensation. Remaining gaps are pagination behavior and filter-combination logic, which are secondary but would help an agent avoid misuse.

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 67%, so the schema carries most parameter meaning. The description adds real value for the undocumented `sort` parameter by explaining the default ordering behavior, and it echoes the condition-hub convention already in the schema. It says nothing about offset/limit pagination or year range semantics, leaving those to the schema.

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 molecular hydrogen studies') plus the search mechanism (keywords and/or filters) and the return payload. It does not distinguish itself from siblings like aggregate_studies, compare_evidence, or find_related_studies, so an agent must infer the split from tool names alone.

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?

'By keywords and/or filters' implies a flexible retrieval use case, and the sorting sentence hints at query-vs-no-query modes. However, it never says when to choose this over sibling retrieval tools such as find_related_studies or get_condition_evidence, nor whether filters combine as AND or OR.

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