keyword_search

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

Goes beyond the annotations by disclosing truncation risk (`max_notebooks` may exclude the notebook you care about), that `notebooks_scanned_ids` reflects actual coverage, and that a failing notebook does not abort the sweep (`notebook_errors` with `ref`). Given readOnlyHint=false while the tool is a search, the mention of cache download via `auto_sync` in the schema helps explain the write-ish profile, but the description itself does not restate that.

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?

Scope and mode are front-loaded in the first sentence, constraints follow. Two short blocks, though the `notebooks_scanned_ids`/`notebook_errors` sentence partly duplicates what the output schema already returns.

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?

Covers the multi-notebook sweep semantics, partial-failure tolerance, and coverage limits — the non-obvious parts for a 7-parameter tool. With an output schema and annotations present, return formats need not be spelled out, so the remaining gap is only the missing comparison to sibling search tools.

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 baseline is 3; the description adds cross-parameter semantics beyond the schema — that `notebook_ids` narrows the sweep only when `notebook_id` is absent, and that `max_notebooks` silently bounds what gets scanned. Useful relational meaning rather than restatement.

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: local BM25 lexical search over one notebook or all of them, explicitly noting it is quota-free. It is distinguishable from semantic/chat siblings by the 'búsqueda léxica BM25 local' phrasing, though it never names alternatives like grep or search_sources.

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?

Explains the key selection rule: omitting `notebook_id` sweeps all notebooks and tags each hit with its origin, which is framed as the way to find where something was documented without opening notebooks one by one. No explicit when-not or sibling comparison, but the usage context is clear.

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