Google Maps MCP

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

No annotations are provided, so the description carries the full burden. It does valuable work by disclosing the return payload shape (local_results with title, rating, reviews, type, address, phone, place ids) and the pagination granularity, but it says nothing about SerpAPI credit cost, rate limits, auth requirements, or failure modes for a 12-parameter network call.

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, front-loaded with the identity of the tool and then the return shape, with no filler. The final sentence largely repeats what the schema already says about q, location/uule and start, which is the only slack.

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 12 parameters, no annotations and no output schema, the description does the important compensating work: it explains what comes back and how the place identifiers chain into google_maps_reviews. The remaining per-parameter details are fully covered by the schema, so only the lack of cost/rate-limit context leaves a gap.

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 gl, hl, tbs, ludocid, device and google_domain is already documented. The description restates q/location/uule/start behavior (including the '+20 per page' hint already present in the schema) without adding new syntax or constraints, 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 ('Search the Google Local pack via SerpAPI') and immediately disambiguates what that means — 'the local business listings Google shows for a query' — which separates it from a general maps search. It also names google_maps_reviews as the downstream consumer of the place identifiers, giving the agent a clear picture of this tool's role.

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 concrete calling context: supply q, optionally location or a pre-encoded uule, and paginate with start at +20 increments. The location/uule exclusivity is called out. It stops short of stating when to prefer this over the sibling google_maps_search, which is the one routing decision an agent still has to infer.

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?

No annotations exist, so the description carries the full burden; it does disclose that results come from a SerpAPI fetch and are returned as a list under `directions`. However it says nothing about caching behavior (no_cache), rate limits, error modes, or whether calls are billable/side-effect free — the very traits an agent needs for a read-through-SerpAPI tool.

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 purpose and endpoint rules are correctly front-loaded, but roughly half the text is a deep enumeration of the return payload (nested trips, details, transit cost fields) that duplicates the existing output schema. Those sentences do not earn their place and bury the actionable parameter guidance.

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 16-parameter, annotation-free read tool, the description covers the essential call contract (how to specify endpoints, how to shape the route) and an output schema covers returns. Gaps remain around caching semantics and failure behavior, but nothing that would cause a mis-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 coverage is 100%, so the baseline is 3, but the description adds real value beyond the schema: it states the mutually-exclusive one-of constraint for start and end points, which the schema does not enforce (zero required fields, no top-level oneOf). It also groups travel_mode/avoid/time as the route-shaping controls.

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 directions between two points via SerpAPI") and immediately distinguishes itself from google_maps_search by naming it as the source of data_ids. An agent can tell this apart from google_maps_search, google_maps_reviews, and google_local_search 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?

Gives concrete usage context: one endpoint must come from start_addr/start_coords/start_data_id, the other from end_addr/end_coords/end_data_id, and route shaping is done via travel_mode, avoid, and time. It does not state when-not to use it or contrast with sibling tools beyond sourcing data_ids, so it stops short of full alternatives 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?

No annotations are provided, so the description carries the full burden, and it does disclose non-obvious behavior: a digit-only id triggers an extra place lookup before the review fetch, and results are paginated with a token from the prior response. It does not mention caching, rate limits, or quota cost, which keeps it short of a 5 for an unannotated tool.

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 sentences, front-loaded with the purpose, then identifiers, then return shape, then pagination. Every sentence adds a distinct decision-relevant fact with no repetition of the 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 11 parameters, no output schema, and no annotations, the description supplies exactly the missing pieces: where identifiers come from, what the response contains (author, rating, text, date, topics), and how to continue paginating. Nothing an agent needs to call it correctly is absent.

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; the description earns an extra point by adding cross-field semantics that the schema states only piecemeal — that a digit-only value is accepted in any of the three id fields and resolved automatically. The remaining parameters (hl, sort_by, no_cache, zero_trace) are adequately covered by their schema 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 ('Fetch the reviews of a Google Maps place via SerpAPI') and immediately distinguishes itself from google_maps_search / google_local_search by naming them as the source of identifiers rather than substitutes. An agent can route between the three siblings 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?

Clearly states the prerequisite ('all come from google_maps_search or google_local_search results') and the selection rule (provide exactly one of place_id/data_id/data_cid), plus the pagination path via next_page_token. It does not explicitly state when to avoid this tool, but the sibling relationship is unambiguous enough that the gap is small.

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?

With no annotations, the description carries the full behavioral-disclosure burden. It usefully explains the two response modes, pagination behavior, and that place_id/data_cid feed google_maps_reviews, but it omits caching/no_cache behavior, zero_trace implications, rate limits, and authentication expectations.

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 description is compact and front-loaded: it starts with the core action, then explains the two modes, pagination, map centering, and the link to google_maps_reviews. Every sentence adds usable information without repeating the 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?

For a complex 23-parameter tool with no annotations and no output schema, the description covers the core search/place workflow but does not describe return-value shape or the behavior of the many filter parameters such as min_rating, price filters, open_state, and no_cache. The schema compensates for parameter documentation, but the overall context is only minimally complete.

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 already documents the 23 parameters thoroughly. The description still adds cross-parameter workflow value by explaining that place_id/data_cid come from a prior search result and feed google_maps_reviews, plus how pagination advances by 20.

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 ('Search Google Maps via SerpAPI') and clearly distinguishes the two operating modes: type=search returns a list, while type=place returns full details for one place. It does not explicitly differentiate this tool from the sibling google_local_search, which is the main clarity gap.

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 clear mode-selection guidance: type=search is the default for queries, type=place requires place_id or data_cid, and pagination uses start with +20 per page. However, it does not say when to use this tool instead of google_local_search or google_maps_directions.

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