file.search

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

Annotations already declare readOnlyHint: true, so the read-only nature is covered. The description adds two behavioral traits: 'deterministic text matching' indicates reproducible results, and the path resolution rule clarifies how relative vs. absolute paths are handled. However, it does not disclose other potentially important behaviors such as case sensitivity, whether search covers file content or filenames, or how glob interacts with path. Given the annotation covers the safety profile, the added context is useful but not comprehensive.

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?

The description is two short sentences with no wasted words. It front-loads the primary purpose immediately ('Search files...'), then adds the path resolution detail. It is compact and easy to parse, earning a perfect score for conciseness and structure.

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?

Given the tool has 5 parameters, no output schema, and only a readOnlyHint annotation, the description is insufficient for an agent to fully understand how to use it correctly. It does not explain what the tool returns (e.g., matching file paths, line numbers), how max_results is applied, whether the search is recursive, or what 'deterministic' implies for the agent (e.g., reproducibility for caching). The path resolution is helpful but many operational details are missing, making it incomplete for proper usage.

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 0%, so the description must compensate. It does add meaning for some parameters: 'text matching' implies the query parameter is the text to search for, 'glob' is a file pattern, and the path resolution sentence explains the path parameter. However, it does not explain max_results (likely a limit) or task_id (likely the task context). Thus it covers 3 of 5 parameters but leaves two unexplained. The description adds partial value but does not fully compensate for the lack of schema descriptions.

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 description clearly states the action and resource: 'Search files using deterministic text matching and a glob.' This distinguishes it from sibling file tools like file.read (which reads a specific file) and file.write. The mention of 'deterministic text matching' and 'glob' also hints at its specific search behavior. It could be more explicit about what is searched (content vs. filenames) but the core purpose is unambiguous.

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?

The description provides no guidance on when to use this tool versus alternatives. It does not mention conditions like 'use file.read to retrieve a whole file' or 'use file.search to locate files by content.' The only contextual note is about path resolution ('Relative paths use the Task worktree; absolute paths use the host OS'), which is about path interpretation, not usage selection. This leaves the agent to infer when to call this tool.

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