drive_search

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

No annotations are provided, so the description carries the full behavioral burden — and it delivers. It surfaces significant non-obvious behaviors: no extra hydration step, checksum fields present only for binary files (absent for folders/docs), always-includes-shared-drives, limit defaulting to 50, 0 meaning auto-paginate with a hard cap of 10000, explicit read-only marking, and YAML output format. Exceptionally transparent for an unannotated tool.

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?

Long but justified — the description front-loads the core purpose and query syntax first, then layers behavior, edge cases, and output format. Every sentence carries information; there's no filler. It slightly loses a point for density and a run-on feel ('pass `0` explicitly' plus multiple parentheticals), but it remains appropriately scaled for the tool's complexity.

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 3 params, 100% schema coverage, no annotations, and no output schema, this description covers all ground any agent needs: return fields, pagination semantics, edge cases (checksum absence on folders), shared drive behavior, read-only safety, and output rendering. Nothing an agent needs to correctly invoke the tool is missing.

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 coverage is 100%, keeping the baseline at 3, but the description adds meaning beyond the schema: it explains the return implications of the query parameter (same syntax as `drive search`), reinforces the limit=0 pagination edge case, and contextualizes the account parameter by implying multi-account resolution. Genuine incremental value.

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?

Opens with a specific verb+resource ('Search Drive files with a Drive query') and immediately anchors it to a known CLI ('same syntax as `drive search`'). The scope is further sharpened by listing the exact fields returned and tying it to the established `omni-dev drive search` command, leaving no ambiguity about what the tool does.

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?

Clearly maintains usage by explicitly naming the CLI it mirrors and, implicitly, the sibling-free purpose. It centralizes key behaviors that help an agent decide when to use this tool: 'full metadata in one call' and 'no separate hydration step' justify using it over a generic search, and the 'Always searches shared drives too' caveat sets expectations. Lacks a fully explicit 'use X instead when' exclusion, but the context is clear.

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