find_files

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

With no annotations, the description carries the full burden and does disclose key behavioral traits: read-only in effect ('not ... write authorization'), operation restricted to configured Owner read roots, and hard bounds on traversal depth and result count. It stops short of stating what happens when a path falls outside the allowed roots (error vs. empty result) or whether results are truncated when max_results is reached, which matters for a bounded search.

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?

Two short sentences, front-loaded with the scope constraint and with no filler. There is mild overlap between the opening clause and the 'Use to discover...' sentence, but nothing that could be cut without losing a safety-relevant constraint.

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 need not be explained, and the input schema fully documents the four parameters. The remaining gap is failure/edge behavior (out-of-root path, truncation signalling), which the description leaves unstated but which is not central to deciding whether to call the 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 description coverage is 100%, so all four parameters (name, path, depth, max_results) already carry descriptions with ranges and defaults. The description adds only contextual framing ('bounded depth/result count', 'under existing Owner read roots') rather than parameter-level meaning, which is the expected baseline-3 situation when the schema does the work.

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 names a specific verb ('discover filenames by name') and a specific scope ('bounded name-only discovery inside configured Owner read roots'), and it explicitly rules out being a content search, which separates it from search_code in the sibling list. It is slightly weaker at distinguishing it from list_folder/list_folder_page, which also enumerate directory contents, but the 'name pattern + depth recursion' framing is still concrete enough for an agent to pick it confidently.

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?

'Use to discover filenames by name under an allowed directory within bounded depth/result count' gives clear positive guidance for when to invoke it. The negative case is partially covered via 'This is path discovery, not a content search or write authorization', which implicitly routes content queries elsewhere, but no sibling tool is named and there is no statement about what to do when a match is expected inside a known single folder (list_folder).

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