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

Annotations already declare readOnly, idempotent, non-destructive and openWorld, so the safety profile is covered. The description adds value by enumerating the concrete result contents (configured account, API version, currency, defaults), which matters because there is no output schema — though it says nothing about what happens on failed credentials.

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 zero filler: the validation purpose comes first, the returned configuration fields second. 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 params and no output schema, the description must carry the return-value burden and it does so by listing the fields exposed. The only gap is error behavior — what the agent should expect when credentials are invalid — which would round out a diagnostic 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?

The tool takes zero parameters, which is the baseline-4 case. There is nothing for the description to disambiguate, and it correctly spends no words on inputs.

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 a specific object ('credentials'), and names what is surfaced: account, API version, currency and defaults. That clearly separates it from the sibling data tools (keyword ideas, volume, forecasts), none of which validate auth, though the description never explicitly contrasts with them.

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 wording suggests a pre-flight/health-check call, but there is no explicit 'use this before X' or 'do not use to fetch account data, use list_accessible_customers instead' guidance. An agent can infer the diagnostic role, but nothing in the text confirms when to prefer it over the siblings.

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 fully covered. The description adds that results come from Google's external geo target dataset, which is useful context. It does not say how ambiguous names are resolved (single best match vs. multiple results), nor mention any rate or batch 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 sentence, front-loaded with the action and ending with the payoff. No filler, no redundancy with the 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?

No output schema exists, and the description does state what is returned (location IDs). For a simple lookup tool with read-only annotations, this is nearly sufficient — only the shape of results for ambiguous or partially matching names is left unstated.

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 67% and the description adds no meaning beyond the schema for any parameter — notably it never explains what `locale` does or how `country_code` disambiguates same-named places. The `names` and `country_code` params are self-documented in the schema, so the gap is not severe, but the description misses an easy opportunity to clarify the third 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 ("Search Google's geo targets by name") plus the concrete outcome ("get location IDs") and enumerates the target types covered. This is unmistakably distinct from the keyword-oriented sibling tools (generate_keyword_ideas, get_search_volume, forecast_keywords).

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 phrase "to get location IDs" implies the use case: call this when you need a geo target ID for targeting. However, there is no explicit guidance on when not to use it, no mention that this is a prerequisite step before other geo-targeted calls, and no pointer to any alternative tool.

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=true, openWorldHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds only the useful detail that results come from Keyword Planner's forecasting; it says nothing about quota consumption, latency of forecast generation, or why the call is open-world.

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?

One sentence plus a short second sentence, with the metrics and the temporal scope front-loaded. Nothing is redundant and both sentences carry new 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?

For a read-only forecasting tool with a rich, well-annotated 6-parameter schema and no output schema, the description covers what is forecast and over what horizon. It could say more about forecast output shape (ranges vs point estimates) but nothing essential to correct invocation is missing.

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 83%, with days, max_cpc, network, language and locations all documented in-schema (including defaults, bounds and geo target ID formats). The description adds no parameter-level meaning beyond that, 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 and resource — forecast impressions, clicks, cost, CTR and average CPC for a keyword set over a future period — and names the engine (Keyword Planner). The 'future period' framing implicitly separates it from historical siblings like get_search_volume, 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?

'Useful for budgeting a paid search campaign' gives a loose usage context, but there is no explicit when-to-use/when-not or routing instruction against generate_keyword_ideas or get_search_volume. Guidance is implied rather than 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 profile (readOnly, idempotent, non-destructive, openWorld), so the description's real contribution is the return-shape disclosure: monthly searches, competition, top-of-page bid range, 3-month change, first-to-last change, and monthly volumes. That is genuine added context, particularly valuable since no output schema exists. It omits cost/quota or rate-limit considerations typical of Keyword Planner calls.

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: purpose first, then the returned metric list. No filler. Slightly dense packing of four input modes into one clause, 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?

For an 11-parameter tool with no required params and no output schema, the description covers both halves well: how you seed it and what each idea carries. Missing only inclusion of the limit/sort/include_monthly toggles, which the high-coverage schema already handles.

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 82%, so the baseline of 3 applies; the schema already documents url, site, limit, network, keywords, language, locations, min_searches, and include_monthly. The description echoes the input modes and names the returned metrics but adds no syntax or format 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?

A specific verb ('Get keyword ideas') plus the named source system (Keyword Planner) and the four supported input modes. An agent can tell what it does immediately, though it never references the sibling get_search_volume/forecast_keywords, which overlaps in domain.

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 description implies usage by enumerating valid input combinations (seed keywords, page URL, whole site, keywords + URL), but it gives no explicit when-to-use/when-not guidance and no routing to siblings. The 'site can't be combined with keywords or url' exclusion lives only in the schema, not in the description.

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 genuine behavioral detail beyond that: results are historical, and close variants grouped by Google are returned alongside the queried keywords, which affects how the agent should interpret output volume.

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 tight sentences: purpose plus returned metrics first, then usage guidance, then an output caveat. No filler and no repetition of schema details the agent will read anyway.

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 what comes back (average monthly searches, competition, top-of-page bids, trends) and warns about grouped close variants, which is the key interpretive detail. Minor gaps remain around what happens for keywords with no data and any quota/cost implications of a 10,000-keyword lookup.

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 86%, so nearly every parameter is already documented in the schema (network, keywords limits, language formats, month patterns, locations). The description only implicitly touches parameters via 'historical' (date range) and 'close variants' (keyword handling), adding little 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 and resource ('Get historical Keyword Planner metrics for specific keywords') and enumerates the exact metrics returned (monthly searches, competition, bid range, trends). This is clearly distinguishable from the discovery-oriented sibling generate_keyword_ideas.

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 sentence 'Use this to check exact keywords rather than discover new ones' gives an explicit when-to-use and a when-not, which implicitly routes the agent toward generate_keyword_ideas for discovery. It stops short of naming the sibling or covering other alternatives like forecast_keywords, so it is clear context without full exclusion 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 declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds something beyond them: the result is scoped to what the 'signed-in user can access,' which discloses an auth-dependent, non-exhaustive result set an agent must account for. Return shape is only implied by 'customer IDs'.

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, zero filler, with the purpose front-loaded and the usage note following immediately. 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?

For a zero-parameter, side-effect-free list operation with rich annotations, the description supplies purpose, auth scoping, and the downstream use of the result. No output schema is needed because the return value ('customer IDs') is named explicitly.

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?

The tool takes zero parameters, so there is nothing for the schema to document and nothing the description needs to compensate for; the baseline is 4. The description correctly implies no filtering inputs are needed to get the full accessible list.

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 Google Ads customer IDs') plus an access qualifier ('the signed-in user can access'), so the scope is unambiguous. No sibling tool (check_connection, keyword/location/language tools) operates on this resource, so the agent can route here 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?

The second sentence gives an explicit use case: 'Use it to find the right GOOGLE_ADS_CUSTOMER_ID,' which tells the agent this is a discovery/prerequisite step. There are no stated exclusions or error-path guidance (e.g., what to do if the list is empty), which keeps it just below 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 readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds that results are reference data with codes and IDs, but says nothing about result size, pagination, or whether the list is 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?

One short sentence, front-loaded with the action and resource, and it also conveys the returned fields. No wasted text, though it could have used the space for a when-to-use clause.

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 reference lookup with one optional parameter, this is close to complete — it states the tool's domain and the shape of returned entries despite there being no output schema. Only minor gaps (exhaustiveness, usage context) remain.

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 optional `filter` parameter is fully documented in the schema. The description adds no extra meaning about filtering behavior, 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?

Specific verb+resource: lists languages that Keyword Planner can target, plus what each entry contains (codes and IDs). It is clearly distinct from siblings like find_locations or get_search_volume, though the description does not explicitly contrast with them.

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 — an agent would call this to obtain language codes/IDs for targeting in other calls — but the description never states when to use this versus alternatives or any prerequisites. No exclusions or routing guidance.

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