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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: partial status meaning, exclusion of proposed protocols, and the distinction between discovery metadata and source reads. It doesn't describe rate limits or error behavior, but the annotations carry the safety burden.

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?

The description is dense but efficient, with each sentence adding distinct information. It front-loads the core purpose and then covers parameters, return values, caveats, and alternatives. Slightly over-packed with domain-specific terms, but no wasted 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?

Given the tool's complexity (4 params, 0% schema coverage, output schema present, 4 siblings), the description covers the key aspects: what it searches, how to paginate, what it returns, what it excludes, and how it differs from siblings. It doesn't explain the output schema structure, but the output schema itself exists to carry that burden. Minor gaps: no explicit statement about query being optional or default behavior.

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%, so the description must compensate. It explains the meaning of 'kind' (all, study, casebook or agent_protocol), the valid range for 'limit' (1-20), and the use of 'next_offset' for pagination. It does not explicitly define 'query' or 'offset' semantics, but the description's coverage of the most complex parameters is strong.

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?

The description states a specific verb ('Find') and resource ('published studies, Casebook and agent protocols by keyword'), and distinguishes itself from siblings by explicitly noting it is 'document search, not analog ranking' and that 'Discovery metadata is not a source read.' This clearly differentiates it from read_research and research_quality.

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?

The description provides explicit usage guidance: it specifies the kind parameter values, limit range, pagination via next_offset, and clarifies when not to use it ('Proposed protocols are not findings', 'This is document search, not analog ranking'). It also directs the agent to use documents[section].read_arguments for exact version-pinned reads, which is an explicit alternative.

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