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

Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false) already cover the safety profile, and the description adds genuinely valuable behavioral context beyond them: response contents (text + relation, no star, total count, myRating when logged in) and the critical data-sparsity caveat that empty returns are normal rather than an error. This prevents an agent from misinterpreting empty results as a failure.

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 short labeled sections front-load the core return value first, then usage guidance, then calibration context. The 口径 section is the longest but earns its place because it carries the unique data-sparsity warning; no sentence is pure filler.

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 read-only call with one required param and a fully documented schema, the main completion risk is response interpretation. The description partially compensates for the missing output schema by naming the response fields (text, relation, total, myRating) and flagging empty returns as the norm, though it stops short of a precise response shape or pagination details.

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 100% — userId, sort (enum with Chinese descriptions), limit (with default), and cursor are all documented in the input schema. The description adds little per-parameter meaning beyond that; its extra details (no star rating, myRating) are response semantics rather than parameter semantics. Baseline 3 is appropriate when the schema does the heavy lifting.

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 opens with a specific verb and resource: '返回某主理人收到的推荐口碑' and specifies the exact return shape (text + relation, no star rating, plus total count), with myRating when logged in. This clearly distinguishes it from sibling read tools like get_creator (works list) and from the write tool endorse_creator.

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 【何时用】 section states the intended scenario explicitly — person due diligence ('谁背书过 TA、以什么关系、说了什么'). It also provides a when-not-to-use signal (endorsements are nearly nonexistent site-wide, so get_creator's works list is more reliable for judging someone) and explicitly names endorse_creator for the write path.

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