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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so safety is covered. The description adds real substance beyond that: which fields each store returns, that Bazaar's extra fields include version_code, histogram, changelog and permission count, and that prices are in Toman with 0 meaning free. Only the shape/format of the response (flat object vs nested) is left implicit.

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 action, then store-specific deltas, then a routing pointer. The store-specific sentences are dense but each carries field-level information an agent would otherwise have to discover empirically; minor redundancy in re-listing the base fields twice.

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 describing returns and does so field by field, including store-specific extras and price units. Complete enough to call correctly and interpret results; only the structural form of the response is unspecified.

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 more by explaining what the store parameter actually buys you: bazaar yields version_code, star histogram, changelog and permission count, while myket yields first publish date and developer_id. That is decision-relevant meaning the enum labels do not provide.

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 ('Get one app's metadata from one store') and enumerates the returned attributes (version, rating, installs, size, developer, price). The 'one store' scope immediately distinguishes it from ap_compare, which 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?

Gives a clear routing rule: use this for a single store, use ap_compare for both stores at once. No explicit exclusion for ap_search or ap_similar, but the single-app scope makes the boundary reasonably clear from context.

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 read-only, idempotent, non-destructive, open-world access, so safety is covered. The description adds genuinely non-obvious behavioral context: slugs are store-specific with an explicit cross-store mapping example, Myket names are Persian, and the Bazaar game list may be incomplete — all of which change how an agent should interpret and reuse results.

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, purpose first, caveats second; nothing is redundant. The abrupt line breaks inside sentences slightly hurt scanability but cost no clarity.

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 read tool with no output schema, the description covers purpose, downstream use, and the data-quality pitfalls that matter. Only the shape of the returned slug list (ordering, approximate count) is left implicit, which 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 coverage is 100% and the single enum is already documented, so the baseline is 3. The description earns above baseline by explaining the consequence of the store choice — that it selects a different slug vocabulary and name language — which is meaning the enum list alone does not convey.

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 adds the downstream consumer ("to pass as ap_top category"), which pins its role relative to the ap_top sibling. An agent can tell this apart from ap_search/ap_app without opening the 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?

The intended use is concrete: call this to obtain a category slug before calling ap_top. It does not state exclusions (e.g. what to do if you already know the slug, or when to skip ap_top entirely), so it stops short of full when/when-not 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, openWorld and non-destructive, so the safety profile is covered. The description adds genuine value beyond that by disclosing the return shape: per-store figures with null for unlisted stores, plus a diff where rating difference is signed bazaar minus myket and version indicates which is newer. It does not say what happens when the package is absent from both stores, which is a meaningful edge case for an open-world lookup.

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, front-loaded with the purpose, then the compared fields, then the return contract. The field list is dense but each item is informative; the line break between the two parts aids scanning without wasted phrasing.

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 read tool with no output schema, the description carries the return contract well: per-store figures, null handling, and diff direction. Minor gap is the unspecified behavior when neither store lists the package, which matters given the openWorld hint.

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 'package' parameter already documents the expected Android package-name format with an example. The description only implies that one package is supplied, adding no syntax, normalization, or lookup semantics beyond the schema. 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 (compare) and resource (one package across Cafe Bazaar vs Myket) and enumerates the exact attributes compared: version, rating, rating count, installs, size, update date, price. This is clearly distinguishable from ap_app (single-store details) and ap_search (discovery).

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 verb and the two named stores, so an agent can infer this is the cross-store comparison tool. However, no sibling is named and no when-not conditions are given (e.g. that ap_app should be used for a single store, or ap_search to find a package name first).

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, openWorld and non-destructive, so safety is covered. The description goes beyond them by disclosing a real asymmetry in results: Bazaar entries carry rating, category, installs and price when paid, while Myket entries only carry name and tagline. It does not mention throttling, empty-result behavior, or partial failure when one store errors.

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 no filler: what it does and returns, then how to use it, then a caveat about differing card contents. The line break mid-sentence and the colloquial 'cards' term slightly blunt readability, but nothing 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?

With no output schema, the description correctly takes on the job of describing return fields and their per-store variance, which is the main thing an agent needs here. What remains thin is failure and edge behavior — zero-hit queries, one store failing while 'both' is selected — for an openWorld search 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?

Schema description coverage is 100%, with page size, limits, language and the store enum all documented inline, so the schema does the parameter work. The description adds only indirect meaning — that the 'store' choice changes which fields appear in results — and nothing about pagination depth or per-store page sizes. 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 (search) plus the exact resource (apps and games across Cafe Bazaar and/or Myket) and names what comes back (package names, ratings, store URLs). That is enough for an agent to separate it from ap_app (lookup), ap_top (rankings), ap_similar (related) and ap_compare 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?

'Use first to find a package name' gives a concrete sequencing rule that ties this tool to the downstream ap_app/ap_compare workflow. It stops short of stating when NOT to use it (e.g. when the package name is already known), so it falls one step shy of the top mark.

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, and open-world behavior. The description adds genuinely new information not in any structured field: that output is grouped, and that Bazaar returns three groups (related, others also installed, similar) while Myket returns one — important for an agent interpreting results with no output schema available.

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 operation, followed by the usage hint. Nothing is wasted, though the parenthetical mid-sentence break slightly interrupts readability and the store-group detail could be tightened.

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, read-only lookup, the definition covers what is returned structurally per store, which is the main thing missing from the schema (no output schema). It does not address ordering, result limits, or empty-result behavior, leaving mild gaps for an agent planning around 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 coverage is 100%, with both `store` (enum with default) and `package` fully documented in the schema itself. The description's reference to "one app" and store-specific group counts adds context but no new parameter syntax, format, or constraint details — 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 states a specific verb and resource — "List apps the store shows as related to one app" — and clarifies the return grouping per store. It is clearly distinguishable from ap_app (single app details) and ap_search (query-based lookup), though it never names those siblings 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?

"Use to find alternatives or competitors of an app" gives a concrete selection context, which separates it from discovery tools like ap_search. It stops short of exclusionary guidance (e.g., that ap_search is for keyword discovery rather than similarity), so it sits below the top of the scale.

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, open-world behavior, so the safety profile is covered. The description adds store-specific semantics that annotations cannot convey (trending vs editorial for 'best', per-store slugs, Myket's 'productivity' actually being utilities). It says nothing about result shape or how ranking ties are ordered.

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?

The core purpose is front-loaded in one sentence, with store-specific qualifications following. The parenthetical enum callouts are useful because they tie prose to the actual enum values, though the line-broken layout and the trailing Myket taxonomy note add density without much structure.

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 should hint at what comes back, and 'list ... of a store' does convey that it is an enumeration of apps. Pagination and page-size limits are already carried by the schema, so the remaining gap is only the exact return shape and ordering guarantees.

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 every parameter is already documented in the input schema — baseline is 3. The description does go slightly beyond by explaining that slugs are store-dependent and that Myket's 'productivity' covers ride-hailing/operator/government apps, but it does not clarify the interaction between 'type', 'category', and 'kind' beyond what the schema states.

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 — 'List the top (best) or newest (new) apps or games of a store' — and pins the scope as 'per category or store-wide', which separates it from a general search like ap_search. It stops short of naming the sibling it is not, so an agent must infer that ap_search handles keyword queries.

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 real operating context: store-wide 'best' means Bazaar's trending list vs Myket's editorial list, and slug conventions differ per store (see ap_categories). The parenthetical spells out which enum value ('best'/'new') maps to which behavior, though it offers no explicit when-not-to-use guidance or a named alternative for keyword lookups.

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