everything_search

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

Adds return-shape disclosure ('Returns paths, size bytes and modification times'), live-index pagination behavior, and a safety guarantee ('Does not read file contents') beyond the readOnly/not-destructive annotations. No contradiction.

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?

Six short sentences, each carrying information; the purpose is front-loaded and the text stays within a compact paragraph. 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?

No output schema exists, but the description states the core return fields. Given 11 parameters and many sibling modes, it doesn't cover how the tool relates to sibling search modes or the meaning of the advanced flags, leaving the full picture incomplete.

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% top-level schema description coverage, the description compensates for the key parameters: query syntax examples and path default scope. However, it leaves sort, limit, offset, regex, match_path, case_sensitive, kind, descending, and filters mostly to their schema names, which is a clear gap.

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 action ('Search the local Everything index') and resource, and adds concrete query syntax examples. It does not explicitly differentiate from the many everything_search_* siblings, so it misses the fifth point.

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?

No sentence tells the agent when to choose this general search over everything_search_typo, everything_search_regex, everything_search_fuzzy, or others. 'No path means all indexed locations' is scope information, not usage routing.

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