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

With no annotations, the description carries the full burden and does real work: it discloses the reduced-scope fallback when locales are absent, that the keyword field is private without them, that the tool is free, and that it only diagnoses (the fixes are written by the user as a PR). Missing return-shape and rate-limit detail, but the mutation/scope profile is well covered.

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?

Long but dense and front-loaded: the check list comes first, then the locales conditional, then cost/ownership. Every clause conveys a distinct fact, though the single sprawling sentence chain could be split for faster scanning.

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 3-parameter diagnostic tool with no output schema, the description says what is checked, what changes the depth of the check, and what the agent gets back in conceptual terms. Return-value format and the appId parameter are the only things an agent might still want.

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 only 33%, so the description must compensate, and it does for the most complex parameter — it tells the agent exactly where `locales` comes from and which metadata files (name.txt, subtitle.txt, keywords.txt, promotional_text.txt, description.txt) map to fields. `storefront` is covered by the schema itself; `appId` gets no description anywhere, which is the remaining gap.

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 (check) and resource (an app's App Store metadata) and then enumerates the exact rule classes it evaluates — character limits, wasted keyword characters, cross-field word repetition, locale indexing, screenshot captions, AI-answer readiness. That enumeration distinguishes it clearly from siblings like keyword_research or check_content.

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?

Gives an explicit conditional: pass `locales` from fastlane metadata files for the full check; without them only the public listing is checked and the keyword field is private. That is a clear when-to-use branch, though it never names a sibling alternative or states when to skip the tool entirely.

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