gmaps.dev

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

Annotations only flag destructiveHint=true; the description goes far beyond by explaining state-dependent outcomes (pending stops at once, free; running keeps arrived places and their credits, lets the in-flight search finish, starts nothing new), the prohibition on already-ended collections, and the API key requirement. This is exactly the context an agent needs before invoking a destructive operation.

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 action and then branches by collection state in a logical order. Mild redundancy between 'costs nothing' and 'Costs no credits', but every sentence carries operative 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?

No output schema exists, yet the description covers preconditions, side effects on results and credits, and auth needs thoroughly. It does not indicate what a successful response returns (e.g., final status or confirmation), which is the only notable 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?

Only one parameter with 100% schema coverage; the schema already documents id including its provenance from create_collection. The description adds no format or sourcing detail beyond that, so the 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 (cancel) and resource (collection) and immediately scopes what cancelling means for each state. An agent can distinguish it from siblings like delete_webhook, get_collection, or list_collections 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 clear conditions for use and a negative condition: a collection that has already ended cannot be cancelled. It does not name an alternative tool for the already-ended case, but no sibling provides that, so the guidance is effectively complete.

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 only declare readOnlyHint=false, destructiveHint=false and openWorldHint=true; the description adds genuinely new behavior: asynchronous fire-and-return semantics, the credit cost model (free to start, one credit per arriving place, saved places free), and the API key requirement. This is exactly the extra context annotations cannot convey.

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?

Six short sentences, front-loaded with the purpose before the async and cost details. Nearly every sentence earns its place, though the cost sentence repeats 'costs nothing' twice and 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?

With no output schema, the description carries the return-value burden and does so ('answers straight away with the collection', re-read to see progress), and it covers auth and billing. It omits what happens on failure and never points at cancel_collection for stopping a run, which a long-running async job would benefit from.

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 economic semantics that the schema lacks: maxPlaces caps how many billable places arrive, and the enrich/credit relationship is hinted at ('each new place costs one credit'). It also frames the geo argument as 'a whole area', reinforcing the area-based search model.

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 an area square by square and collect places into a collection, capped at maxPlaces. An agent can tell this is the asynchronous 'start a bulk collection' tool rather than a point lookup. It never names a sibling (search_places, quote_collection, get_collection) explicitly, so it falls short of full sibling differentiation.

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 clear operational context: the call returns immediately with the collection, then runs in the background, and the agent should re-read the collection to check progress. That tells an agent how to use the result. It stops short of naming alternatives (e.g. quote_collection to estimate cost before committing, or search_places for immediate one-off results).

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=false, destructiveHint=false and openWorldHint=false, so the mutation/safety profile is covered. The description does add genuinely useful behavior beyond that: the returned link works without an API key for 24 hours, the calling tool needs an API key, and the export costs no credits – all auth/cost/expiry details annotations cannot express. However it omits whether the export is produced synchronously or must be polled, which is the main behavioral unknown for a create 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?

Front-loaded with the core action and format list, followed by four short sentences that each carry distinct information (snapshot semantics, link expiry, API key, cost). Only minor waste: 'csv, json or xlsx' in the first sentence duplicates the schema enum, and 'so share it only with people who should see the file' is advisory rather than operational.

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 cover the key return artifact (a shareable link valid 24 hours without an API key) plus cost and auth requirements. What is missing for a three-parameter creation tool is the lifecycle: whether the link is returned immediately or the export must be fetched later via get_export, which an agent needs to sequence calls 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 description coverage is 100% and every parameter (format, locale, collectionId) is documented in the schema, including the xlsx 50,000-place limit and the locale default, so the schema does the heavy lifting. The description only echoes the format list and adds no syntax or constraint information the schema lacks, 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 (get a link to a collection's places as one file) plus the supported output formats, which is more precise than the terse title 'Export a collection'. An agent can distinguish it from get_export (retrieve an existing export) and from quote_collection/create_collection 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?

Implies usage by describing snapshot semantics ('the places the collection holds now, even if it is still running') and a sharing caveat, but never states when to call this versus the sibling get_export or what to do if the export is still being produced. The routing decision between create_export and get_export 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?

Beyond the annotations (readOnlyHint=false, openWorldHint=true), the description discloses several behavioral traits an agent could not infer: the signing secret is returned once and never again, the payload carries counts and a link but not the places themselves, and it requires an API key plus a paid plan while consuming no credits.

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?

It is front-loaded and every sentence carries information, but the conversational phrasing ("Tell us where to POST", "instead of asking us every few seconds") is more colorful than strictly necessary for a specification.

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 covers the return surface (the one-time signing secret), along with auth requirements, plan gating, cost, and payload shape. Nothing material for 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 100%, so url, events, and description are already fully documented, setting the baseline at 3. The description adds payload/secret context but no additional per-parameter syntax or format meaning.

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 action and resource: registering a URL where events are POSTed when a collection ends. It is clear what the tool creates, though it relies on the title ("Add a webhook endpoint") and never names itself relative to siblings like update_webhook or delete_webhook.

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 rationale for using this over polling ("instead of asking us every few seconds whether it is done"), which is strong when-to-use context. It does not, however, distinguish itself from sibling webhook tools such as test_webhook or update_webhook.

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 destructiveHint=true and readOnlyHint=false, and the description goes well beyond them by specifying exactly what is destroyed: the endpoint and the record of prior deliveries. It also adds auth requirements (API key, paid plan) and cost behavior (no credits), which 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?

The destructive effect is front-loaded, followed by the alternative, the rationale for that alternative, then prerequisites and cost. Every sentence carries distinct, actionable information with no padding.

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 single-parameter destructive tool with no output schema and full annotation coverage, the description supplies the destruction semantics, the safer alternative, auth/prereq constraints, and cost profile. Nothing needed to invoke it correctly 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?

With 100% schema coverage and only one parameter, the schema already documents id thoroughly. The description adds no format or sourcing detail for id, and its mention of 'enabled' refers to a different tool's parameter, 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 ('Stop sending to an endpoint and forget it') and immediately distinguishes its scope from the pause/disable path, which is the main sibling ambiguity with update_webhook. An agent can tell what this destroys versus what update_webhook would do 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?

Explicitly gives the alternative and the condition that selects it ('To pause one instead, set enabled to false'), plus prerequisites (API key, paid plan) and cost (no credits). It never names the sibling tool update_webhook, so an agent must infer which tool carries the 'enabled' flag, which is a small remaining gap.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond the annotations: no API key is required and the call consumes no credits, which is exactly the auth/quota information an agent needs.

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, zero filler, and the core purpose is front-loaded before the operational caveats about API key and cost.

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 no-parameter, read-only listing tool with an empty schema and no output schema, the description covers purpose, payload content, and access conditions. Nothing an agent needs in order to call it correctly 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?

The tool takes zero parameters and the schema covers 100% of what is implied, so the baseline is 4. Nothing about parameter semantics needs to be, or is, explained in the description.

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) plus the exact resource (projects credited by gmaps.dev) and what each entry contains (licenses and notices). It is unambiguously distinct from every sibling tool, all of which concern collections, webhooks, exports, places, or usage.

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 gives access conditions ("No API key needed. Costs no credits.") but never says when to reach for this tool or what an agent might otherwise do instead. Usage is implied rather than stated; there are no real alternatives among the siblings, so the gap is minor but present.

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, destructiveHint=false, and openWorldHint=false, so safety is covered structurally. The description adds value beyond that: it states an API key is required and that the call costs no credits, plus that repeated reads are the intended update mechanism — practical operational context not present in the annotations.

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 with the outcome front-loaded ('See where a collection has got to') followed by the concrete payload and then the operational notes. Slight wordiness in 'how much of the area is searched, how many places have arrived, and what it has cost so far', but every clause carries 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, the description must convey what comes back, and it does list the three returned signals (coverage, arrivals, cost). Combined with the API-key and credit-cost notes, an agent has enough to call it correctly; only the distinction from get_coverage remains unaddressed.

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 schema already explains that the id is 'the collection's id, as create_collection returned it'. The description adds nothing about the id parameter, so the baseline of 3 applies — the schema does all the work here.

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 names the specific resource (a collection) and the three facts it returns — search progress, places arrived, and cost so far — which is more concrete than the title 'Read a collection' alone. It does not, however, distinguish itself from the sibling get_coverage or list_collections, so an agent must infer the boundary. Clear verb+resource with no sibling differentiation.

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?

'Read it again whenever you want an update' gives a real usage pattern (polling this tool for state changes), which is better than nothing. But it names no alternative and no exclusion — notably it never mentions create_webhook, which exists as a push-based sibling. Usage is implied rather than contrasted.

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?

Adds behavior beyond the readOnly/destructive/openWorld annotations: 'Needs an API key. Costs no credits and starts nothing.' Auth requirement, cost model, and side-effect profile are exactly the extra context annotations can't carry, and all three are disclosed.

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 sentences, each carrying distinct payload: what it returns, when to use it, and operational constraints. Purpose is front-loaded and 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?

No output schema exists, so the description must convey returns itself, and it does: searched fraction, last-search time, and count of saved places. Combined with the usage and cost context, an agent has everything needed to call it 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 description coverage is 100% and already documents geo forms, keyword semantics (per-term coverage), and lang. The description restates 'area' and 'term' at a high level without adding 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: reporting how much of an area has been searched for a term, when, and how many saved places exist. It's clearly a read/inspection operation, distinguishing it from the collection/search siblings, but it never names a specific alternative tool.

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 decision context: 'Use it to decide whether to collect again or just read the saved places.' That tells the agent when the tool is useful, though it stops short of naming the concrete alternative tools or stating hard exclusions.

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 (readOnlyHint=true, destructiveHint=false, openWorldHint=false), and the description layers on non-obvious behavior: a 24-hour link TTL, the 404 conditions, the API-key requirement, and that it costs no credits. These are exactly the traits 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?

Three short sentences, front-loaded with what the tool returns, then the expiry constraint, then auth/cost. Every sentence carries information the agent needs; nothing is padding.

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 compensates by naming the return payload (download link) and its lifetime. With one fully described parameter and annotations covering safety, 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 coverage is 100% and the single id parameter is fully documented in the schema, including its UUID format and that create_export returned it. The description adds no additional format or sourcing detail, so the schema does the heavy lifting and the baseline of 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 ('Read an export') with the primary payload named (the download link) and a scope constraint (only while the link still works). It also implicitly distinguishes itself from the sibling create_export by telling the agent to make a new export rather than re-use this one.

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 failure conditions (after 24 hours, or once the collection's places are deleted, it answers 404) and the corrective action (make a new export from the collection). An agent knows exactly when this call is valid and what to do when it isn't.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new operational context: the 404-on-unsaved-place semantics, the API key requirement, and the fact that the call costs no credits.

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 with no filler, front-loading what the tool does and immediately following with the constraint and the alternative. 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?

For a one-parameter read tool with no output schema, the description covers identity, failure mode, auth requirement, cost, and the correct alternative path. Nothing needed to invoke it correctly 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?

There is a single parameter and schema description coverage is 100%, so the schema already documents the accepted identifier formats. The description restates the same identifier list without adding format, precedence, or validation detail beyond it, which is the expected baseline when the schema does the heavy lifting.

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 ('Read one saved place') and enumerates the four accepted identifier forms, so the agent knows exactly what kind of lookup this is. It also distinguishes itself from search_places without needing to open 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?

Explicitly rules out search behavior ('It never searches'), states the failure condition (unsaved place returns 404), and names the alternative plus the condition that selects it ('searching its area with search_places brings it in'). This is textbook when/when-not/alternative 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, non-destructive, and closed-world, so the safety profile is covered. The description adds two pieces of context annotations cannot express: the API-key requirement and the fact that the call is free. It stops short of describing response shape beyond the enumerated totals, so not a 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?

Two sentences, front-loaded with the returned content and finishing with the auth/cost constraints. No filler; every clause adds 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?

There is no output schema, so the description carries the burden of describing return values, and it does so concretely (plan, used, remaining today/month, per-key totals) while also covering auth and cost. Nothing an agent needs before calling 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?

Zero parameters, so there is nothing for the description to disambiguate. Baseline for a parameterless tool.

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 and enumerates exactly what is returned: plan allowance, used, remaining today and this month, plus per-API-key totals. No sibling tool overlaps with credit usage, so it is trivially distinguished from the collection/webhook/place tools.

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?

"Needs an API key. Costs no credits." gives a clear prerequisite and a cost condition, which is real usage guidance. It does not name alternatives or exclusions, but none of the siblings are substitutes for this query.

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, non-destructive, closed-world), yet the description adds real value beyond them: ordering (newest first), that a total is returned for pagination, an API-key requirement, and that the call costs no credits. Auth and cost disclosure are exactly the kind of context annotations cannot convey.

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 the resource and ordering, then the filter, then the operational constraints. The aside "so you know how many more there are" is mildly padded but justifies the total-count mention.

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 covers return ordering and the presence of a total count, and it discloses auth and cost. Pagination mechanics via offset are left entirely to the schema, which is a minor remaining 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 limit, offset, and the status enum are already fully documented, including the enum values. The description only restates the status filter's purpose, adding no syntax or format detail beyond the schema, so the baseline of 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 resource (collections) and scope (newest first, paginated total), which distinguishes it from get_collection (singular) and create_collection. It does not explicitly name a sibling, but the plural listing scope makes the intent 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?

"Filter by status to find the ones still running" gives one concrete usage cue for the status parameter, but there is no explicit guidance on when to prefer this over get_collection or how it relates to other listing tools. Usage is implied rather than spelled out.

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, destructiveHint=false, openWorldHint=false, but the description adds real operational context the annotations cannot: 7-day retention, API key plus paid-plan requirement, and zero credit cost. Retention and cost/auth prerequisites are exactly the kind of facts an agent needs before planning a 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?

Four short sentences, each carrying distinct payload: what is returned, when to use it, retention, and auth/cost. Front-loaded with the resource and ordering, with no filler or repetition.

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, yet the description enumerates the return fields (event, arrival status, attempt count, server response), so the agent knows what it will get. Combined with retention, auth, and cost notes, nothing needed to invoke this correctly 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 100% and both parameters (id, limit) are fully documented in the schema, including the 1-100 range and newest-first ordering. The description's 'one endpoint' and 'newest first' merely restate the schema, adding no new syntax or constraint detail, 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 concrete verb+resource with scope and ordering: 'What we sent to one endpoint, newest first', then enumerates the fields returned (event, delivery status, attempt count, server response). This is unmistakably distinct from list_webhooks (endpoint configuration) and test_webhook (sending a test), so an agent can route to it 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?

'This is where to look when an event never showed up' gives an explicit diagnostic trigger for using the tool. It does not name alternative tools (e.g., test_webhook for proactive checks, list_webhooks for config) or state exclusions, so it falls short of the 5-level when/when-not/alternatives 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 establish read-only, non-destructive, closed-world behavior, but the description adds substantial context beyond them: ordering is newest first, each endpoint shows whether it still receives events and why delivery stopped, secrets are not returned after creation, and the tool requires an API key plus a paid plan while costing no credits.

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 front-loaded with the core purpose and return content, followed by security, billing, and prerequisite details. Every sentence adds useful information, and none 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?

With no input parameters and no output schema, the description carries the return-value burden well: it explains ordering, event-receiving status, stopped-delivery reasons, and secret handling. It also covers auth and plan requirements, making it complete for this zero-parameter list 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 has zero parameters, so there are no parameter semantics to document and the baseline is 4. The description correctly does not invent parameters, though there is no additional parameter behavior to explain.

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 resource, webhook endpoints, and the scope, endpoints the user has added, newest first. It is clear what the tool returns, though it does not explicitly name or distinguish itself from the closest sibling, list_webhook_deliveries.

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 strongly implied by 'Every endpoint you have added,' and the description adds useful prerequisites: API key and paid plan required, no credit cost. However, it does not explicitly say when to use this versus alternatives such as list_webhook_deliveries or how to inspect a single webhook.

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/destructive/openWorld, and the description adds meaningful context beyond them: requires an API key, consumes no credits, initiates nothing, and enumerates what the quote reports (recent coverage, already-saved places, remaining searches, max credit cost).

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 purpose in the first clause and follows with two short, high-value sentences about auth and cost. Slightly long single opening sentence but no wasted text.

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 compensates by enumerating the four figures the quote returns, so an agent knows what it gets back. A minor gap is that it doesn't describe response format or how the maximum credit cost is composed.

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 is fully documented in the schema. The description references concepts like keywords and area 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 ('See what collecting an area would cost before you start it') and frames the operation as a pre-flight estimate, which cleanly separates it from create_collection.

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 says to use it before starting a collection and clarifies it 'starts nothing' and 'costs no credits', making the timing and cost condition clear. It does not name create_collection as the follow-up alternative, but the pre-flight framing makes the intent unambiguous.

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 declare readOnlyHint=false and openWorldHint=true, and the description explains exactly why this is not a pure read: a search can spawn a collection, each new place costs one credit, and cost is capped by `limit`. It additionally discloses the API key requirement and the 60-second `wait` ceiling, well beyond structured fields.

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 purpose and the free-cached-results benefit, then the cost/collection mechanics, then follow-up and auth. The middle sentence is dense with a colon and multiple clauses, but each sentence carries distinct information rather than 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?

For a complex, credit-metered, partially-asynchronous tool with no output schema, the description covers the mechanics an agent must understand: caching, collection creation, per-place cost, the limit cap, and how to retrieve late arrivals. It does not describe the shape of returned place objects, which is the main remaining 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 coverage is 100%, so baseline is 3, but the description layers on real meaning: `limit` doubles as the maximum credit cost of a search, and `wait` is framed as waiting for newly collected places rather than a generic timeout. That cost binding is not derivable from the schema alone.

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 places') and grounds it with a concrete example ('bakeries in Curitiba'), including both the 'what' (keywords) and 'where' (geo) axes. It is unmistakably distinct from the sibling set, which is dominated by collections, exports and webhooks.

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 clear operational context: results already saved return instantly and free, and 'search again later, or read the collection, to get the new ones' tells the agent how to follow up. It stops short of naming sibling tools or stating explicit when-not-to-use conditions, so it is strong but not fully directive.

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?

Adds real context beyond the annotations: it is synchronous ('answers straight away with the delivery'), requires an API key and paid plan, and costs no credits. It does not explain the destructiveHint=true / openWorldHint=true profile — that the ping hits an external endpoint — so it falls short of a 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?

Four short sentences, none wasted, action and purpose front-loaded, with cost and prerequisite notes appended last where they belong.

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 still tells the agent what the immediate response is (the delivery) and where the server's actual reply appears (the deliveries list), plus auth and billing constraints. Nothing needed to invoke it correctly 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 100%, and the schema itself documents both 'id' (as returned by create_webhook) and 'message'. The description adds nothing about either parameter, so the baseline of 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 — sends a test 'ping' event to one of your webhook endpoints — and immediately distinguishes it from real traffic ('before a real collection depends on it'). An agent can separate test_webhook from create_webhook or list_webhook_deliveries 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 an explicit reason to use it (verify your code reads the payload and the signature checks out) and points to the sibling tool that completes the flow ('read the deliveries list a moment later'). Prerequisites are also named (API key, paid plan).

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?

Goes well beyond the annotations: discloses partial-update semantics ("whatever you leave out stays as it was"), that re-enabling resets the failure count to zero, and the operational prerequisites (API key, paid plan, costs no credits). The destructiveHint=true annotation is not contradicted – the endpoint can be switched off.

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 short sentences, front-loaded with the capability summary, then the reactivation workflow, then state semantics, then prerequisites. No filler and no repetition of schema content.

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 4-parameter partial-update tool with no output schema, the description covers capability, state semantics, reactivation workflow, and auth/billing prerequisites. An agent can call it correctly without opening anything else.

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 75%, and the description still adds meaning on top: it maps rename to the description field and explains the state transition and side effect of enabled=true that the schema's one-line note doesn't fully convey. The id parameter and event enum semantics are left entirely to the schema, which is acceptable.

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 plus the three mutable facets (events, name, enabled), so an agent immediately knows this is a partial update of an existing webhook. It never names create_webhook or delete_webhook, so sibling routing rests on inference, but the scope is 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?

Gives a concrete when-to-use scenario: reactivating an endpoint after deliveries were stopped by fixing the server and setting enabled to true. That's stronger than generic context, though it never states when NOT to use it (e.g., to change the target URL, use delete+create).

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