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

Annotations already carry the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description goes well beyond them: it explains truncated semantics (limit hit vs complete, and how to resolve it) and warns that permission-denied subtrees are silently skipped so zero results aren't proof of absence outside /sdcard. This is exactly the operational context annotations cannot express.

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 core purpose, then layers matching semantics, return shape, and the truncation/permission caveats. Every sentence carries information, though the density is high and it runs long for a search tool.

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?

With no output schema, the description correctly documents the return shape ({ ok, remotePath, query, count, truncated, matches }) and the failure/edge behavior of the underlying device shell. An agent has everything needed to call it and interpret results.

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%, so the baseline is 3, but the description adds detail the schema lacks: query is case-insensitive (schema omits case sensitivity) and describes the glob characters, plus it links limit to the truncated return field. That is genuine added meaning over the structured fields.

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 (search) plus resource (a directory subtree for files whose NAME matches) and explicitly scopes matching to names, not contents. It also identifies the sibling it mirrors (ios_file_find), letting an agent distinguish it from the device_file_list/stat family without opening a 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?

The description pins down when name-matching (vs content matching) is the right approach and how to react to a truncated result, which is usable context. It stops short of explicitly naming the sibling to prefer for full listing (device_file_list) or metadata (device_file_stat), so guidance is clear but not exhaustive.

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