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

Annotations already declare readOnly/idempotent, so the description adds cost ('one flat price per call'), cross-platform id mixing behavior, and platform-specific differences (Google adds installs). It stops short of describing response shape or pagination of the comparison itself, so it's strong but not exhaustive.

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 core capability and metric list, then routing, then examples. Dense but each clause carries information; the parenthetical metric list is slightly packed but justified given no output schema.

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 fully enumerates return content (store rating, price, version, review sample metrics, top complaints, per-metric leaders) and discloses cost. An agent has everything needed to decide and call 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 coverage is 100%, so baseline is 3, but the description adds real meaning: the 2-10 constraint, that all apps share one storefront, and that Apple ids and Google Play package names can be mixed in a single call. That clarification goes beyond the per-parameter schema text.

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 (benchmark/compare) and resource (2-10 apps in one storefront), and enumerates the exact metrics returned. It explicitly positions itself against siblings, noting review_insights is for single-app depth.

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 prerequisites ('Get ids from search_apps first'), an explicit exclusion routing to review_insights for single-app deep dives, plus concrete example queries. Both when-to-use and when-not-to-use are covered.

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 cover the safety profile (readOnly, idempotent, non-destructive, open-world), and the description adds genuinely new operational context: the billing model is per review returned, pages are ~50 reviews, default 1 page, and hard cap of 10 pages (~500 reviews). That cost/limit disclosure is exactly the kind of trait annotations cannot express.

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?

Four dense sentences with zero filler, and the primary action plus when-to-use clause is front-loaded before the pricing detail. Slightly packed but every clause 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?

There is no output schema, so the description carries the return-shape burden and does so by naming the fields returned (rating, title with Apple-only caveat, text, app version, date, helpful votes, Google developer replies). Combined with cost and page limits, nothing material is missing for correct invocation.

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 lang, sort, pages, store, app_id and country are all documented in the schema already (including Apple/Google inference rules and ranges). The description only restates page sizing ("~50 per page; default 1 page") and adds no syntax or format detail beyond the schema, 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?

States a specific verb+resource ("Fetch raw reviews for one app") and enumerates the returned fields, immediately distinguishing it from the sibling that produces aggregated results. An agent can tell this apart from review_insights without opening either 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?

Gives an explicit positive trigger ("user wants to read or quote actual reviews or you need text for custom analysis") and an explicit negative trigger with the named alternative ("For summaries, complaints or 'what broke', call review_insights instead"), even noting why (one flat-priced call). Nothing is left to inference.

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 read-only/idempotent/non-destructive, but the description adds real behavior beyond them: a flat per-call price independent of pages/countries, the versionDeltas fallback to "last 3 days vs earlier" when version data is thin, and the shape of each returned block. It stops short of error modes or data-freshness limits, so 4 rather than 5.

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 highest-value routing sentence ("Best first call for any question about an app's user feedback") before the return-value enumeration. The versionDeltas clause is dense and nested with parentheses, but every sentence carries usage or output information.

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 and 8 parameters, the description carries the return-shape burden and does so thoroughly, including fallback behavior. Gaps are minor: no statement on data freshness/recency window or failure behavior when an app has few reviews.

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 decision-relevant semantics: price is flat regardless of pages/countries, so an agent need not minimize them, and the versionDeltas fallback clarifies what happens when since_version is omitted. It does not explain keyword_limit or quotes behavior beyond the schema, so not a 5.

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?

Specific verb+resource (analyses recent reviews) plus an explicit enumeration of what is returned: rating distribution, average rating per version, complaint phrases with share and quote, versionDeltas, sample quotes. It also names the two siblings it is not (get_app_reviews, compare_apps), so an agent can route without opening schemas.

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 states both a positive trigger ("Best first call for any question about an app's user feedback") with concrete exemplar queries ("why are users unhappy with X", "what broke in the last update") and negative routing to alternatives for raw review text and multi-app benchmarking. When-to-use and when-not-to-use are both explicit.

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, openWorld, non-destructive), so the bar is lower. The description still adds cost/latency context ('Cheap, one call') and enumerates the returned fields, including the store-dependent 'installs' for Google, which is genuinely additive.

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 purpose and the key payoff (the app id), then usage conditions, then routing. Every sentence carries information; 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 compensates by enumerating the return fields, and it covers store selection, cost, and next-step tools. An agent has everything needed to call this correctly and route onward.

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 lang, term, limit, store, and country are all documented in the schema itself. The description reiterates store: "google" for Android but adds no syntax or format detail beyond the schema, 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 ('Find apps by name or keyword') plus the downstream value ('get the app id the other tools need'). This clearly distinguishes it from siblings get_app_reviews, review_insights, and compare_apps, which all consume the id this tool returns.

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?

Explicit triggering conditions are given: when the user names an app ('Duolingo','Calm') or a category ('budget apps'). It also names the follow-on tools (review_insights, compare_apps) and the store selection rule, leaving little to inference.

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