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

With no annotations, the description carries the full burden and discloses a genuinely non-obvious quirk: the cn source's status column is empirically always 1 with no semantics and returns null. It also notes status filtering only works on source=global and that a few Chinese status values are matchable by fuzzy words, which prevents real misuse.

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?

A single dense paragraph, front-loaded with the core purpose before source-specific caveats. Every clause earns its place, though the packing of source differences, the status quirk, and the field list into one block makes it slightly heavy to scan.

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?

No output schema exists, and the description compensates by listing the shared return fields (trial_no/title/drug/target/indication/phase/status/sponsor). Combined with the source and enum caveats, it covers what an agent needs to call correctly, with only minor gaps around keyword-matching 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 coverage is 100%, so the baseline is 3, but the description adds meaning the schema does not: phase uses the std_phase Chinese enum on cn (e.g. III期 / Phase 3), and status is exact-match for English enums yet fuzzy-match for Chinese terms. This clarifies parameter behavior beyond the schema text.

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+resource (检索临床试验 / search clinical trials) and crisply splits the tool into two sources with their record counts. It names the exact return field set, so an agent can distinguish it from the sibling get_clinical_trial_detail without opening any schema.

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?

Gives clear conditions for choosing source=cn vs source=global (database size, filterable fields, status semantics), which is exactly the decision the caller must make. It stops short of explicitly naming the alternative detail tool or stating when NOT to use this search, so it is strong context rather than full routing guidance.

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