search_files

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavior: no-filter returns everything up to `limit`, and a timed-out search returns partial results with a notice. It doesn't cover result ordering or how truncation is signalled beyond 'says so', but that is a minor gap against solid annotation coverage.

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?

Front-loaded with the core capability, then immediately routes to alternatives, then covers edge cases. Every sentence carries distinct information: scope, exclusions, default behavior, timeout semantics. 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?

For an 11-parameter read tool with full schema coverage and no output schema, the description covers the essential unknowns: unfiltered behavior, the result cap, and partial results on timeout. Return-value shape is left unspecified, which is acceptable since the schema carries no output contract, but a note on result ordering would round it out.

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 100%, so all 11 parameters are already documented in the schema, including wildcard, size units, and date formats. The description only re-states the `limit` cap ('up to `limit`') and adds nothing about parameter syntax beyond the schema, which is appropriate at the 100%-coverage baseline.

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) with clear scope (a folder and everything below it) and enumerates the filterable facets: name, extension, size, modified date. It explicitly names the two siblings it is not (list_files, get_dir_size), so an agent can distinguish it without opening any schema.

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?

Gives explicit when-not rules: 'For what's in one known folder, use list_files; for how much space a folder uses, use get_dir_size, not a search.' It also documents the no-filter case ('returns everything under the folder, up to limit'), so an agent knows what an unqualified call does.

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