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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the leading 'Read-only' largely restates structured data. The description does add useful content beyond annotations by naming what the payload contains (app metadata plus latest version and state per platform), but says nothing about lookup failure behavior or rate limits.

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?

A single front-loaded sentence with no padding, and the returned-field list is compact. The 'Read-only.' lead-in is mildly redundant with the annotations but is short enough not to be wasteful.

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 one-parameter, non-mutating lookup with no output schema, the description tells the agent what identifying input forms exist and what the response covers. Only missing piece is explicit routing versus list_apps.

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% and the single 'app' parameter is documented with all three accepted identifier forms (name, bundle ID, numeric Apple ID), so the schema carries the load. The description adds no identifier-format guidance beyond what the schema provides; baseline 3 applies.

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+resource ('Shows one app's details') and enumerates the fields returned (bundle ID, Apple ID, SKU, primary locale) plus latest version/state per platform. The singular 'one app' implicitly distinguishes it from list_apps, but no sibling is named explicitly.

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?

Usage is only implied: 'one app' signals a single-record lookup versus list_apps or list_app_store_versions. There is no explicit statement of when to prefer this tool or when to reach for a sibling instead.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so "Read-only" adds nothing new. The description does add real value beyond annotations by disclosing the permission scoping (results limited to what the API key can see) and the returned identity fields. It says nothing about pagination behavior or how to traverse beyond the limit.

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?

Two short sentences, front-loaded with the read-only status and the core scope before the optional filter. No filler, and every sentence carries information the agent needs.

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 two-parameter, non-destructive listing tool with no output schema, the description is nearly complete: it names the resource, the access scope, and the fields returned, which substitutes for the missing output schema. The only gap is pagination/traversal behavior for the limit parameter.

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 both parameters are already documented in the schema, giving a baseline of 3. The description's "filter by part of the name or bundle ID" essentially restates the schema's own wording for 'search' rather than adding semantics such as matching rules for the limit 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?

States a specific verb and resource ("Lists the apps in App Store Connect") plus the access scope ("that your API key can see") and returned fields (bundle IDs and Apple IDs). It implicitly contrasts with the singular get_app sibling via the plural 'list', but never names or explicitly distinguishes it.

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 final sentence gives clear guidance on the optional filtering behavior (partial match on name or bundle ID), which implies the main usage pattern. However, there is no explicit when-to-use guidance versus get_app (single app lookup) or the other list_* siblings, and no exclusions or prerequisites stated.

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

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

Annotations already cover the safety and idempotency profile, so 'Read-only' is largely redundant, but the description earns credit by disclosing ordering ('newest first') and the shape of returned records (platform, state with enumerated lifecycle values, release type) despite there being no output schema. It stops short of describing truncation or how the limit interacts with ordering across pages.

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?

A single front-loaded sentence plus a brief safety prefix; nothing is padded. The leading 'Read-only.' duplicates readOnlyHint from the annotations, which is the only wasted wording.

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 simple read-only list tool with only three fully documented parameters and no output schema, the description supplies the essentials an agent needs: what is returned, in what order, and which fields matter. Adding more would tip into redundancy with the schema and annotations.

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 fully documents app, limit, and platform, and the description adds no syntax or format detail beyond it. The mention of platform and state refers to returned data rather than filter semantics, so the baseline 3 applies.

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 gives a specific verb and resource ('Lists an app's App Store versions') and adds scope details (per-app, newest first). It does not explicitly contrast with the nearest sibling, list_builds, so an agent must infer that builds and App Store versions are different objects, but the resource naming makes the distinction reasonably discoverable.

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?

Usage is only implied: an agent can infer this is the tool for enumerating an app's App Store version records, but there is no explicit when-to-use, no mention of when to prefer list_builds or get_app, and no prerequisites such as needing the app to exist in App Store Connect.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the leading "Read-only" sentence merely repeats structured data. The genuinely additive part is the disclosure of what each result shows (internal/external status, public link on/off), which matters since there is no output schema. Pagination behavior via limit/cursor is left to the schema.

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?

Two short sentences, front-loaded and free of filler. The opening "Read-only" is wasted given the annotations, but the rest earns its place by naming the returned attributes.

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 simple paginated read with full schema coverage, the description supplies the crucial missing piece — what fields each group carries. It omits any mention of paging behavior, but cursor and limit are self-documenting in the schema.

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% — all three parameters (app identifier formats, limit default/max, cursor source) are documented in the schema itself. The description adds no additional meaning about parameters, so baseline 3 applies.

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 ("Lists an app's TestFlight beta groups") and even enumerates the key attributes returned (internal vs. external, public link state), so an agent knows exactly what it gets. It does not explicitly distinguish itself from siblings like list_beta_testers or get_app, which keeps it out of 5 territory.

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?

Usage is implied by the purpose: fetch the beta groups belonging to a given app. There is no statement of when to prefer this over list_beta_testers, no prerequisites (e.g., does the app need TestFlight enabled), and no exclusions.

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

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered; "Read-only." largely restates that. The description does add value beyond annotations by enumerating the returned fields (name, email, status values, invite source), which matters because there is no output schema.

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?

A single dense sentence with the read-only nature front-loaded and no padding. The leading "Read-only." duplicates the annotation slightly, but the rest of the sentence is tight and information-dense.

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 four-parameter filtered list tool with a fully documented schema and no output schema, the description covers scope, the group-narrowing option, and the shape of the results including status values. An agent has everything needed to call it and interpret the response.

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 every parameter including the group filter, limit and cursor is already documented in the schema. The description only adds the relational nuance that group scopes within an app, which is a modest supplement rather than new semantics.

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 ("Lists TestFlight testers") and scopes it to an app or one of its beta groups, so it is distinguishable from list_beta_groups. It stops short of naming sibling tools explicitly, which keeps it out of the top band.

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?

Usage is implied: call it when you need the testers of an app or a specific beta group. There is no explicit when-not guidance and no named alternative for related queries (e.g., listing the groups themselves via list_beta_groups).

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

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so "Read-only" is largely redundant. The description does add value beyond them: it discloses newest-first ordering, enumerates the fields present in each result (which matters since there is no output schema), and explains what the status values signify.

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?

Two compact sentences, with the resource and ordering front-loaded and the filtering tip last. The opening "Read-only." is a minor duplication of the readOnlyHint annotation, but nothing else is wasted.

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?

Because there is no output schema, the description's enumeration of returned fields and result ordering carries the return-value burden, and it does so well. Pagination and parameter details are fully covered by a 100%-described schema, so an agent has everything needed to call this correctly.

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 every parameter is already documented in the schema, and the enumerated status/platform values are spelled out there too. The description restates the status values and adds a small hint about filtering by "processing", but adds no syntax or semantics beyond the schema baseline.

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 specific verb and resource ("Lists an app's uploaded builds") and immediately adds the ordering ("newest first") plus the exact fields returned (version, build number, platform, processing status, upload time, expiry). This clearly distinguishes it from siblings like list_app_store_versions, which return a different resource.

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?

One concrete tip is given: "Use status 'processing' to see builds still being processed by Apple." That helps with a specific filter state, but there is no guidance on when to choose this tool over list_app_store_versions or get_app, nor any exclusions or prerequisites — usage is only implied.

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

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so "Read-only" is redundant. The description earns credit for details annotations cannot carry: the default newest-first ordering and the fact that review text is returned trimmed, which sets expectations about content fidelity. It stops short of mentioning pagination or result-volume behavior.

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?

Two tight sentences with the most decision-relevant facts first (read-only, resource, ordering) followed by the returned fields and filters. Nothing is padded or restated.

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 no output schema, the description usefully enumerates the returned fields, which is the main gap it needed to fill. The one omission is that results are paginated via the cursor parameter and a "More available" line; an agent could miss that without reading the schema closely.

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 all five parameters are already documented with types, bounds, and formats. The description only restates that rating and territory act as optional filters, adding no new syntax or interaction semantics beyond the schema, which lands at the baseline.

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?

"Lists an app's App Store customer reviews" gives a specific verb plus resource, and the surrounding clauses pin down scope (single app), ordering (newest first), and returned fields. The resource name alone distinguishes it from siblings like list_builds, list_beta_testers, and list_app_store_versions.

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?

Usage is only implied: the description establishes that this is the reviews-listing tool and notes the optional rating/territory filters, but never states when to reach for it versus get_app or the version-listing siblings, nor any prerequisites such as needing a resolvable app identifier. Adequate but leaves routing to inference.

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