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 the description's job is to add context beyond that, which it does: store-dependent field availability, approximate/rounded installs, currency in Toman with 0 = free, and no binary download. It stops short of error behavior (e.g., unknown package) 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?

Front-loaded with the core purpose and return fields, then progressively adds store-specific and unit caveats; every sentence carries information. The middle sentence is dense and list-like, which slows scanning slightly, but nothing is filler.

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 must carry the return-value burden, and it does so well: field list, store-specific extras, precision caveats, and currency semantics. Remaining gaps are minor (failure modes, whether fields can be null for a given store).

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, but the description earns extra credit by explaining the consequence of the store enum value (Bazaar adds version_code, histogram, changelog, permission count; Myket adds first publish date and developer_id). The package parameter's meaning is only implied by 'one app's metadata'.

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+resource ('Get one app's metadata from one store') and immediately enumerates the returned fields, so the agent knows exactly what the tool produces. It also explicitly distinguishes itself from ap_compare and from APK-download tools, making sibling selection unambiguous.

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 routes the agent to an alternative with a condition ('To see both stores at once use ap_compare') and states a scope exclusion ('Metadata only: no APK download'). It does not, however, contrast with ap_search or ap_similar, which occupy adjacent lookup use cases.

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 the safety profile is covered. The description adds real context beyond them: slugs are store-specific (Bazaar 'tools' = Myket 'productivity'), Myket names are Persian, and the Bazaar game list is not guaranteed complete.

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 short sentences, front-loaded with what it does and the consumer, followed by only the caveats an agent actually needs (store divergence, Persian naming, non-exhaustive game list). Nothing is padded.

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 carries the burden of explaining the return and does state it returns category slugs plus important caveats about store divergence. It does not describe the concrete return shape (list of strings vs. objects with names), which is the one remaining gap for a tool with no output 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% and the single 'store' parameter is an enum already documented in the schema, so the baseline is 3. The description reinforces store-specific behavior but adds no syntax or format detail about the parameter itself.

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 ('List the category slugs of a store') and ties the output to its downstream consumer ('to pass as ap_top category'), which cleanly separates it from ap_top, ap_search, and the other siblings. An agent knows exactly what this returns and why.

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 a clear usage context: call this to obtain valid category slugs before invoking ap_top, and it warns that the Bazaar game list is a verified subset rather than exhaustive. It stops short of explicitly naming a 'do not use this for X' exclusion, so it falls just under the top bar.

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 the bar is lower, yet the description adds genuinely non-obvious behavior: null values when the app is absent from a store, the diff direction (bazaar minus myket), and the caveat that ratings are not shared between stores. It does not mention auth, rate limits, or error behavior, so it falls short of a full behavioral picture.

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 compared fields, then the return shape and diff semantics, in two tight sentences. Every clause carries information; nothing is redundant with 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?

With no output schema, the description must explain the return value, and it does: per-store figures plus a diff identifying the newer version and the rating delta. Combined with full annotation coverage, an agent has everything needed to call and interpret this tool.

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?

There is a single parameter with 100% schema description coverage, including format and examples ('ir.mci.ecareapp'), so the schema carries the semantics. The description only refers to it obliquely as "one package" and adds no syntax or constraint 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?

States a specific verb (compare) and resource (one package across Cafe Bazaar and Myket) and enumerates exactly which fields are compared: version, rating, rating count, installs, size, update date, price. This is clearly distinguishable from siblings like ap_app (single-store detail) or ap_search.

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?

Provides concrete use-case triggers ("is the app up to date on Myket?", "which store rates it higher"), which tells the agent when this tool is the right pick. It stops short of explicitly naming when NOT to use it or pointing to ap_app/ap_search as the single-store alternative, so it is clear context rather than full routing guidance.

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 readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuinely useful non-annotation detail: what a result card contains and the asymmetry between stores ('Myket cards only name and tagline (ap_app has the rest)'), which sets expectations for result completeness.

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-loaded with what it does and what it returns, followed by routing and per-store caveats; every sentence carries information. The clause 'ap_app has the rest' is slightly parenthetical but still earns 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?

No output schema exists, so the description must convey what comes back; it names package names, ratings and store URLs and then qualifies store-specific payload differences. Pagination and limits live in the schema, so the remaining gap is minor.

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%, including store enum semantics and per-store page sizes, so the schema does the heavy lifting. The description adds only indirect meaning (search is by name, Persian or English is already in the schema), so baseline 3 is appropriate.

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 ('Search Cafe Bazaar and/or Myket for apps and games by name') plus the scope of each store, and distinguishes itself from siblings by naming ap_app and ap_compare as the follow-up tools. An agent can tell it apart from ap_top/ap_categories 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?

Explicitly prescribes the workflow ('Use first to find a package name, then ap_app for details or ap_compare for both stores'), which is clear routing guidance. It does not cover when an agent should skip search entirely (e.g. ap_top for charts or ap_categories for browsing), so it stops short of full when/when-not coverage.

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). Beyond that, the description discloses a behavioral trait the annotations do not: the per-store variation in returned result groups (three for Bazaar, one for Myket), which materially affects how an agent interprets the output. Error/empty-result behavior is not 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?

Two tight sentences with zero filler; the core behavior and its store-specific nuance come first, and the usage/workflow hint follows. Every clause earns 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 no output schema, the description usefully explains the shape of the result (grouped related/also-installed/similar) and points to next-step tools, which is what an agent needs to act. Minor gaps remain around result size, pagination, or behavior for an unknown package.

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%, with both parameters (package, store) documented including an example package name and enum values, so the schema does the heavy lifting. The description adds no syntax or format detail beyond the schema, making 3 the correct 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?

States a specific verb (list) and resource (related apps for one app), and adds the store-dependent result shape (Bazaar: three groups; Myket: one). This is clearly distinguishable from siblings like ap_search and ap_top without opening any 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?

Explicitly names the use case ('find alternatives or competitors of an app') and the follow-on workflow ('then ap_compare or ap_app on a result'). No explicit when-not-to-use or negative routing against siblings such as ap_search, so it stops short of a 5.

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 readOnly/idempotent/open-world, and the description adds real behavioral context beyond them: store-wide 'best' is a trending or editorial list with no ranking guarantee, and store-specific category labeling differs (Myket 'productivity' means utilities). It does not describe the returned payload shape, which is the remaining gap.

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-loaded with the core verb and the two modes, then follow-on instructions. Slightly dense, and the parenthetical unpacking of Myket's 'productivity' category is a tangent that could be trimmed, but nothing is redundant.

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 six-parameter, read-only listing tool with no output schema, the description covers selection logic, prerequisites, and follow-up tools. The one omission is what the results look like (packages, names, ranking fields), which matters because there is no output schema to fall back on.

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 baseline is 3, but the description adds meaning the schema cannot: category slugs differ per store, the same slug maps to different real-world app sets, and category is only valid with kind='best'. That is genuine disambiguation beyond the enum descriptions.

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: list the top ('best') or newest ('new') apps/games of a store, per category or store-wide. It also immediately disambiguates the two modes and names the sibling tools (ap_categories, ap_app, ap_compare) that handle adjacent jobs.

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 explicit routing rules: get category slugs from ap_categories first, then use ap_app or ap_compare on a package. It also states the constraint that 'new' requires a category while store-wide only works for 'best', which is exactly the decision an agent must make before calling.

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