ios_find

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: it reads the tree before compaction, reports matches the digest dropped, and each match says whether it is 'shown' or 'hidden'. It also explains the diagnostic meaning of a hidden match. This goes beyond the annotations without contradicting them.

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 moderately sized but every sentence earns its place. It front-loads the core purpose, then provides usage guidance, behavioral details, and a diagnostic hint. It is slightly longer than strictly necessary but the length is justified by the need to differentiate from ios_observe and explain the hidden/shown semantics.

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 the tool's complexity and the rich annotations (readOnly, openWorld, idempotent), the description is complete. It explains when to use it, what it returns (matches with shown/hidden status), how to interpret results, and how to use the budget parameter. The output schema exists, so return values need not be detailed. Nothing an agent needs to call it correctly 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 description coverage is 100%, so the schema already documents all three parameters. The description adds meaning by explaining the 'budget' parameter's role in deciding 'shown' and instructing to pass it whenever set on ios_observe. It also clarifies the 'text' parameter is matched case-insensitively, which is in the schema but reinforced. The description doesn't repeat parameter names but adds contextual guidance for the budget parameter.

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 clearly states the tool searches the screen's accessibility tree, including what the digest hides. It distinguishes itself from ios_observe by explaining it reads the tree before compaction and reports matches the digest dropped. The verb 'search' and resource 'accessibility tree' are specific and unambiguous.

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 explicitly says when to use this tool vs ios_observe: use ios_observe with a query when you want a usable digest with refs; use ios_find when ios_observe shows nothing matching but text is on device, or when a tap keeps missing. It also names the alternative and the condition that selects it, leaving nothing to inference.

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