search

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

With no annotations, the description carries the full burden — and it delivers richly: never downloads the vault, folds diacritics, expands synonyms, accepts quoted phrases, treats a bare commit sha specially, excludes archive/superseded notes by default, and reports how many results it hid. This is exceptional behavioral disclosure for a search 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?

Roughly 70 words packed with signal, front-loaded with the most operationally important fact ('CHEAP — start here'). Every sentence earns its place: cost behavior, match scope, normalization, syntax, special case, filtering defaults, and output reporting. No 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?

The core usage path is fully specified — what is searched, how query syntax works, default exclusions, and what the result reports. The output schema covers return shape, and the cost/staleness behavior is disclosed. The remaining gap is the eight filter parameters that go unexplained despite zero schema descriptions, leaving agents to guess at their formats and interactions.

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 0%, so the description must compensate. It explains the critical parameter well — query semantics (fields matched, quoting, diacritics, synonyms, sha lookup) and the defaults for include_archive/include_superseded. However, 8 of 11 parameters (tag, area, kind, limit, since, folder, status, path_prefix) receive no semantics beyond their names.

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 — 'Full-text search over the local SQLite index of the vault' — with exact matching scope (title, summary, tags, body). The 'CHEAP — start here' opener and the file-operation siblings make it unmistakably distinct from read_file/write_file/list_files etc.

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?

Opens with explicit routing guidance: 'CHEAP — start here', telling the agent to try this tool first. 'It never downloads the whole vault' explains the cost tradeoff that justifies that recommendation. It stops short of naming alternatives or stating when not to use it, though the non-overlapping file-op siblings reduce the need.

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