cite

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

With no annotations, the description carries the full burden and does well: it discloses the return shape ({quotes[], best}), the empty-result behavior (quotes:[], 🟡), the judgment_request branch with follow-up action, and the rule not to rewrite text. It omits error/permission behavior, so not a 5.

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?

Front-loaded with the core purpose and return shape, then the query-formatting and branch guidance. Dense but every sentence carries information; the emoji/symbol shorthand adds minor noise.

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, but the description supplies the return shape, the empty case, and the alternate phase flow, which is what an agent needs. The unexplained `limit`/`top_k`/`use_kernels` parameters are the main remaining gap.

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 only 20% (advisor_dir documented), so the description must compensate. It explains that `query` accepts a list of formulations and should be in the corpus language (English), which is real information beyond the schema, and hints at kernel anchoring (implying use_kernels). However `limit` and `top_k` are left entirely unexplained.

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: retrieve ready-made quotes for an argument, explicitly contrasting with manual assembly ('ручной сборки'). It does not name a sibling such as `retrieve` to disambiguate, so it stops short of a 5.

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 concrete usage context: how to formulate `query` (list of phrasings, in the corpus language), what to do when nothing matches verbatim, and routes the agent to `gate_verdict` in the phase=judgment_request case. It never states when NOT to use this tool or how it differs from the sibling `retrieve`, so no explicit exclusion.

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