search

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

Annotations already declare readOnly/idempotent/closed-world, so safety is covered; the description goes further by explaining that results are citations meant only to judge whether a chunk is worth expanding, that snippets are capped at 300 characters, and that empty or truncated results carry a `CODE: 说明` hint with next steps. It does not, however, describe ranking/scoring behavior or how many hints might appear, leaving modest gaps for a retrieval tool.

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 purpose, then return shape, then use/don't-use, then edge-case handling, using bold labels as visual anchors. Every line carries distinct information and nothing is repeated.

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?

An output schema exists, so return structure need not be re-specified, and the description still adds the crucial framing that snippets are citation previews rather than evidence. Combined with explicit when/when-not routing against both siblings and hint-handling for empty/truncated results, nothing an agent needs to call this correctly is missing.

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%, so every parameter — including the RAG_MAX_TOP_K convergence note and the list_sources pointer for doc_type/department — is already documented in the schema. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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 opening line names a specific verb and resource — hybrid retrieval (lexical + semantic) over an enterprise knowledge base returning snippet-level hits — and immediately defines the return unit (chunk_id + ≤300-character snippet + section path). This cleanly separates it from `fetch`, which is explicitly framed as the tool for full document content.

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?

It states both sides explicitly: use when you need facts, policies, processes, or document原文 as evidence; do not use when the doc_id is known and full content is wanted — go to `fetch` or `resource`. The alternative is named with the exact condition that selects it, so no inference is required.

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