Search files

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

With annotations providing readOnlyHint=true and idempotentHint=true, the safety profile is covered. The description adds significant behavioral context beyond annotations: cache duration (5 min), cache-bypass mechanism (refresh=true), path exclusions (.git/node_modules), timeout behavior (25s partial results with partial:true), index behavior (PROTON_DRIVE_INDEX=1 may cause stale:true), and the meaning of walk.complete=false. These are valuable operational details not visible in the schema or annotations.

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 dense paragraph that front-loads the core purpose, then immediately covers the return shape and critical behavioral caveats. Every sentence provides actionable information: the return structure, cache behavior, timeout handling, and index behavior. No padding or repetition.

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 14 parameters with full schema coverage, no output schema, and annotations covering safety, the description is remarkably complete. It explains the return structure, cache and timeout behaviors, index interaction, and operational failure modes (partial:true, walk.complete=false, stale:true). An agent has enough information to call this tool correctly and handle its responses.

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 the schema already documents all 14 parameters with examples and constraints. The description adds one important semantic detail: 'Filters are ANDed', which clarifies how multiple filter parameters combine. However, it doesn't add format details or edge cases for individual parameters beyond what the schema provides.

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 opens with a specific verb+resource combination ('Find files/folders under a path') and explicitly lists the filter dimensions available (name, type, extension, size, date). This clearly distinguishes it from siblings like drive_list (which presumably lists without filtering) and drive_tree (which shows hierarchy). The 'in one walk' phrase hints at a single-traversal approach, though the distinction from drive_list isn't explicitly stated.

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 provides clear conditions for using advanced features: 'refresh=true re-reads' when cache is stale, 'call again' when partial:true is returned, and 'repeat the call or pass refresh:true' when index-based results are stale. However, it does not explicitly state when to use drive_search vs drive_list or drive_tree, nor does it say when NOT to use this tool. The guidance is operational rather than comparative.

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