search_project

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

The description discloses important behaviors beyond the readOnlyHint annotation: default file types, case sensitivity default, maxResults with truncation behavior, and that 'Skips hidden entries and the .mcp directory'. This gives the agent full understanding of the tool's behavior and limitations.

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 a single, front-loaded paragraph. Every sentence is informative: purpose, usage, defaults, return shape, exclusions. No redundant or filler content.

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 no output schema, the description explains the return format { matches, truncated } and mentions it skips hidden entries. Parameter defaults and search behavior are fully covered. This is complete for a straightforward search tool.

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% with descriptions for all parameters. The description adds value by restating defaults and adding truncation behavior for maxResults. While not drastically new, it provides a concise summary that helps the agent understand parameter interactions.

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 starts with 'Plain-text (substring) search across project files', clearly stating the verb and resource. It further specifies use cases: 'find references, callers, or signatures across the codebase', which distinguishes it from sibling tools like get_project_files or scene operations.

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 explicitly says 'Use to find references, callers, or signatures across the codebase', providing clear context for when to use this tool. However, it does not explicitly state when not to use it or mention alternative tools, though the sibling list doesn't include another search tool.

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