grep_search

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

readOnlyHint=true already establishes the safe-read profile, so the description's contribution is the return shape (matching lines, context, line numbers, paths) and the feature set (path_glob, case sensitivity). Since an output schema exists, the return-value description is partly redundant, and it omits throttling/truncation behavior for high-match queries.

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 tight sentences, front-loaded with purpose then return shape then supported features. Every sentence carries information, though the return-format sentence loses some value against the existing output schema.

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 7-parameter tool with zero schema documentation, the description covers the search semantics and two flags but leaves workspace, sub_dir, and max_matches unexplained. An agent can call it on defaults, but cannot reason about workspace scoping or result caps from the definition.

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?

With 0% schema description coverage the description must carry the params, and it only explains path_glob (with a concrete glob example) and case sensitivity. sub_dir, workspace, and max_matches remain undocumented in both places, so the compensation is partial.

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 (search) and resource (files in the workspace) and pins the mode as 'exact regex or substring', which implicitly contrasts with semantic/fuzzy siblings like deep_search or search. It does not explicitly name any sibling alternative, so an agent must still infer the boundary, keeping it from 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?

Usage is implied by 'exact regex or substring' — use it when you know the pattern — but there is no explicit when-to-use, when-not-to-use, or named alternative among the many search siblings (deep_search, git_search, search_symbols). The contrast is left for the agent to construct.

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