find_files

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

With no annotations, the description carries the full behavioral burden and does disclose real traits: matching is name-only (not content), ranking is by query-term matches, include scopes the path set, and an empty query enumerates candidates. It omits tie-breaking/ranking order, behavior on zero matches, and any auth or performance notes, so it is informative but not complete.

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 terse sentences, zero filler, and the highest-value constraint ('Does not search file contents') is front-loaded immediately after the purpose statement.

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?

An output schema exists, so return values needn't be described. The description covers the matching scope and the empty-query edge case, which is enough for an agent to invoke it correctly; the only real hole is the undocumented top_k parameter.

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 explains query (empty implies listing) and include ('scopes paths'), but top_k is never mentioned in either the schema or the description, leaving one of three parameters entirely undocumented.

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 and resource: 'Rank workspace paths by query-term matches in their names,' and adds a scoping boundary ('Does not search file contents'). That boundary separates it from content-search siblings conceptually, but it never names find_evidence, find_symbols, find_usages or select_context, so the agent still infers which sibling to prefer.

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 exclusion 'Does not search file contents' and the note 'an empty query lists candidates' imply when the tool fits, but no alternative tool is named and no explicit when-to-use/when-not routing is given. Usage is inferable rather than stated.

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