Search service files

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

Far exceeds what the annotations provide (readOnly/idempotent/non-destructive only). The description discloses depth 20, 500-result and 10-second caps, never-walked paths (/proc, /sys, /dev), 10 searches/min per service, the 202 async polling behavior with waitSeconds, explicit files:read grant requirements, connector scope vm:files:read, availability gating with reason codes, and the 423 2FA-lock response.

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 search semantics and tightly packed with semicolon-separated clauses; nearly every clause carries operational information. The dense run-on formatting of auth/availability/error clauses makes it harder to scan than a structured breakdown would be, but there is little true 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?

Covers the full lifecycle an agent needs for this call: match semantics, caps, rate limit, async polling with waitSeconds, the continuation tool, auth scope, availability preconditions with reason codes, and the 423 case. With no output schema, the description still explains truncated/timedOut return meanings, leaving nothing material 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 60%: `name` (required, pattern-only) and `limit` have no schema description, and the description compensates by explaining the substring/glob matching semantics and the 500-result ceiling. `path` default and `waitSeconds` default 30 are already in the schema, so the description adds most value where the schema is silent rather than uniformly.

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 precise verb and resource ('Find entries by name below a directory') and immediately narrows it with matching semantics (case-insensitive substring or glob with * ? [ ]), which cleanly separates it from list_service_files, stat_service_file and read_service_file. An agent can tell what this tool is without opening the 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 clear operating context: rate limit, truncation semantics, and explicit routing to get_service_file_operation for the async continuation path with the warning 'never repeat the call'. It does not explicitly say when to prefer this over list_service_files, so sibling routing is only implied by the name-matching semantics.

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