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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint, so safety is covered. The description adds real behavioral context beyond that: the tool is free, it does not apply fixes ('the fixes are yours to write, as a PR'), and the keyword field is only visible when repo locales are supplied. Missing only auth/permission notes.

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-loads the audit scope before the operational guidance, with no filler sentences. The parenthetical file list is dense but earns its place by disambiguating the nested parameter.

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?

For a read-only audit with no output schema and a complex nested input, the description covers what is checked, what differs between the two modes, and how to source the locales payload. Return format and result shape are the main omissions, but those are acceptable given there is no output schema to be consistent with.

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 only 33% and the nested `locales` object has no field-level descriptions, so the description has to compensate; it does so by mapping the fields to concrete fastlane filenames (name.txt, subtitle.txt, keywords.txt, promotional_text.txt, description.txt). `appId` is left unelaborated, but the locales guidance adds substantial meaning over the raw 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?

States a specific verb and resource (audit an app's App Store metadata) and enumerates the concrete checks: character limits, wasted keyword characters, cross-field repetition, locale indexing, screenshot captions, AI-answer readiness. This is far more specific than sibling names like app_metadata or check_content, letting an agent route to it directly.

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?

Clearly explains the two operating modes: passing `locales` from fastlane metadata triggers the full check, omitting it limits the audit to the public listing (with the keyword field unavailable). It does not explicitly name sibling alternatives or exclusions, but the conditional usage is unambiguous.

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