Why a tester cannot install a build

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description's closing 'Read only' merely repeats that, earning no credit. What it does add is genuine diagnostic scope: the specific failure modes examined and that it reports profile device counts. It says nothing about result shape or what happens when a check cannot be determined, so the added value is moderate.

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 failure modes are packed into one front-loaded sentence that states the question being answered before the details, then two short follow-ups for usage and safety. It is dense but every enumerated cause is informative; the trailing 'Read only' is the only line that does not earn its place.

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 only two well-documented parameters and no output schema, the definition is nearly self-sufficient: an agent knows the trigger, the optional device scope, and the categories of findings to expect. The main residual gap is the response shape — it hints that device counts are returned but not how findings are structured or whether issues are ranked.

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 and both parameters are already documented. The description reinforces the UDID's meaning ('the tester's device') and implies the build scopes the diagnosis, but adds no format, ID-resolution, or precedence detail beyond the schema.

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 names a concrete diagnostic purpose — explaining why a tester's device refuses to install a given build — and enumerates the concrete causes it inspects (signing type, profile expiry, device list, Developer Mode, enterprise trust, test key, minimum OS version). That is far more specific than the name alone. It stops short of a clean verb+resource framing and never names a sibling, so an agent must infer the boundary with build_info/build_installs rather than being told.

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?

It gives an explicit trigger phrase ('Use it to answer "my tester cannot install"') plus guidance on the optional parameter ('Pass the tester's UDID to check their device too'), which is exactly the when-to-use signal an agent needs. There are no when-not-to-use conditions or named alternatives for adjacent tools such as build_info or build_installs.

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