search_manual_procedure

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

With no annotations, the description carries the full burden and delivers: it discloses decision_support_only=true, not_validated_for_hospital_deployment=true, not_pre_submission_storage=true, verify_current_official_source=true, and a privacy constraint (不得輸入病人資料). These are meaningful operational caveats beyond what the schema could show, though the flags are terse and unelaborated (e.g., what enforcement or failure mode occurs).

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 dense clusters — scope enumeration, operational flags, and query examples — each earn their place, and the scope is front-loaded. The flag block is written as terse key=value syntax rather than prose, which is compact but slightly cryptic, and the chapter enumeration is long; minor structural polish would make it a 5.

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 single-parameter free-text search tool with an output schema present, the description covers scope, accepted input semantics, and safety constraints thoroughly. Minor gaps remain: no mention of result limits, language expectations for queries (examples are Chinese), or pagination, but these are not critical given the rich output 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 coverage is 0%, so the description must fully compensate, and it does. It explains acceptable input types (specimens, steps, terms, clause numbers), gives concrete examples in Chinese (糞便檢體, 包裝, 不良檢體, 名詞解釋, 屍體解剖), and specifies the behavior for clause-number queries (returns sub-steps). This is exactly the guidance an agent needs to construct a correct query.

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 ('Search every part of the CDC manual that is not a table row') and enumerates the exact coverage: chapters 1, 3-6, 8, 9, appendix forms, and figure captions. The explicit exclusion of table rows distinguishes it from the many structured get_* sibling tools without needing to open their schemas.

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 gives clear context on what to search (prose sections versus table rows) and provides concrete query examples including clause numbers ('3.5 會一併回它底下的步驟'), which effectively tells an agent how to invoke it. It does not explicitly name sibling alternatives or enumerate when-not-to-use conditions, but the table-row exclusion strongly implies the structured get_* tools are the alternative.

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