Deliver Screenshots Audit

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=true, so the safety profile is covered. The description still adds value beyond them: the precise invariant being verified (order, COMPLETE state, MD5) and the read-only guarantee reinforced as "No writes." It does not discuss failure modes or what happens on a mismatch.

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?

Three compact lines with the core comparison front-loaded, followed by a Use-when clause and a Returns line. Every sentence earns its place and none repeats the name or title.

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?

An output schema exists, so the Returns summary is supplementary rather than required, and it is included anyway. For a low-complexity two-parameter read-only audit with full schema and annotation coverage, this is complete; only a note on what to do with a failing audit 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% and both parameters (app_dir, bundle_id) carry clear examples in the schema. The description adds no parameter-level meaning, so the baseline of 3 is correct.

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 (audit), the resource (App Store Connect screenshot sets vs. local fastlane/screenshots files), and the exact comparison criteria (order, COMPLETE state, MD5). This clearly distinguishes it from deliver_screenshots (the writer) and screenshot_sync, so an agent can select it 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?

"Use when: after deliver_screenshots and before submission" gives an explicit lifecycle position and names the prerequisite sibling, plus "No writes" bounds it. It stops short of naming a fallback alternative if the audit fails, but the trigger context is unambiguous.

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