Cosmic's Camp Map

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuinely new behavioral context: that it returns a request-scoped validity answer ('whether the current request carries a valid pass') and external purchase links, which the annotations do not convey. It stops short of describing the return shape or any freshness/latency characteristics.

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 is front-loaded in the opening clause, which is good, but the description repeats the same feature list twice ('offline maps, the full scouting list, work-week picks, the full hunting view' then 'offline use, more spots, work-week picks, hunting details'), so the closing sentence does not fully earn 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 parameters and no output schema, the description carries the burden of explaining what comes back, and it largely does: pass benefits, pricing tiers (CA$55/yr, CA$5/mo), purchase links, validity status, and hand-off instructions. The main remaining gap is sibling disambiguation, which 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?

The tool takes zero parameters, so per the rubric the baseline is 4. The description correctly implies no input is required, and there are no parameter semantics to document.

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 a specific resource (the Camp Map Pass) and enumerates what the tool returns: feature comparison vs. the free map, prices, purchase links, pass hand-off instructions, and current-request pass validity. It is clear on its own but never distinguishes itself from siblings like pass_status (which also reports pass validity) or start_pass_purchase (which handles buying), so overlap is left unresolved.

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 by the topics covered ('how to buy', 'upgrading' suggest when a user asks about the pass). There is no explicit when-to-use statement and no guidance about choosing between this tool, pass_status, and start_pass_purchase, despite clear functional overlap with both.

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 and openWorldHint=true, so the safety profile is covered. The description adds genuine behavioral context on top: the response is point-scoped, it aggregates several data classes, and hunting detail is withheld unless a Camp Map Pass is held. It stops short of 5 because it says nothing about how current the data is or how it behaves on water/unresolvable points.

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 dense sentence, front-loaded with the primary purpose ('Land status at a point') followed by the returned data classes in a scannable list. Every clause carries information; only the trailing hunting/pass clause slightly dilutes the front-loading.

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 carry the return-value burden, and it largely does — it enumerates land classifications, camping rules, signal estimation, logging activity, road surface, and fire-ban pointers. Remaining gaps (freshness, behavior at invalid or marine coordinates) are minor for a read-only 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 coverage is 100% — both lat and lng carry descriptions with WGS84 units and range constraints — so the schema does the heavy lifting. The description adds nothing about the coordinate parameters (e.g. precision expectations), so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific resource ('land status at a point') and enumerates the concrete payload — camping rule, special areas, per-carrier signal, logging, nearest road surface, fire bans. That is far more specific than the bare tool name 'check_spot'. It does not, however, distinguish itself from near-siblings like find_spots or confirm_spot, so it stops short of a 5.

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: an agent can infer this is for evaluating one known coordinate before camping. There is no explicit when-to-use statement and no mention of find_spots (discovery) or confirm_spot (commitment) as the alternatives. The one conditional given — hunting details require a Camp Map Pass — is a data-gating note rather than routing 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 only declare the write/open-world/non-idempotent profile, while the description adds genuinely non-derivable behavior: it requires the user's Camp Map Pass key, it shares a daily cap of 10 stored reports, and the data is consumed by the next scouting-list build. It stops short of explaining what happens on a repeat submission despite idempotentHint=false.

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 dense sentences, front-loaded with the core action and followed by the key operational constraints; almost every clause (credentials, rate cap, downstream consumer) earns its place. The parenthetical enum list is slightly redundant with 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 mutation tool with no output schema, the description covers credentials, rate limiting, and downstream effect, which is most of what an agent needs. Missing only edge behavior on duplicate writes (consistent with idempotentHint=false) and failure handling.

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%, with lat/lng and name already documented in-schema. The description's recital of the outcome values duplicates the enum already present in the schema and adds no format or selection guidance beyond it, 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 ('Stores what the user found at a camping spot') and enumerates the discrete outcomes, so an agent knows exactly what is being recorded. It does not explicitly distinguish itself from near-siblings like check_spot or report_conditions, which keeps it short of a 5.

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 context is implied by 'read by the next scouting-list build' and the pass-key requirement, which tells the agent when the write is meaningful and what credential is needed. However, there is no explicit when-to-use vs check_spot/report_conditions guidance or any stated exclusion.

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 readOnlyHint and openWorldHint, so the bar is lower, yet the description still adds substantive behavior: results are ranked, the free tier caps at the top 3 plus a count of what the Camp Map Pass would add, and the pass raises the cap to `limit`. It omits auth/rate-limit or error behavior, but the tiering disclosure is valuable 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?

Three dense sentences with the purpose front-loaded and zero filler; each sentence carries distinct information (what it returns, free/pass caps, rental filtering). The parenthetical aside is the only slightly loose element.

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 result shape, and it does cover ranking, the free 3-spot cap, the 'how many more' count, and the pass-driven limit. It stops short of describing what fields each spot record contains (signal strength, distance, access type), which leaves a minor gap for a 6-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 83%, so the baseline is 3, and the description goes beyond it by tying `limit` to the pass tier and clarifying that access=rental keeps spots on pavement or within 500 m of unpaved road, a sharper rule than the schema's 'on or near pavement'.

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 with scope qualifiers: ranked camping spots near a point that are remote but have carrier signal. This cleanly separates it from siblings like hunting_spots and check_spot, which the agent can distinguish 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?

Explains the free-vs-pass result tiers and when to use access=rental (rental agreements excluding unpaved roads), which is genuine usage context. It does not, however, name alternative siblings (e.g., check_spot or plan_trip) or state when NOT to use this 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 cover read-only/open-world safety, but the description adds the non-obvious paywall gating (Camp Map Pass, CA$55/yr or CA$5/mo) and the content boundary around regulations. It does not state rate limits or response shape, but against the annotation baseline this is a solid additive disclosure.

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 compact sentences with the gating requirement front-loaded before content and exclusions. The pricing detail ('CA$55 a year or CA$5 a month') is arguably surplus for tool selection but is plausibly user-facing context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description should say more about what comes back – the presence of check_spot/confirm_spot siblings suggests spots carry identifiers that flow into later calls, which is never explained. Gating and content scope are covered, so it is adequate but not complete for an agent's full workflow.

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 description contributes nothing about lat, lng, limit, or radius_km. Schema coverage is 75%, so lat/lng/radius_km carry their own docs, but 'limit' is undocumented in both places. With the schema doing most of the work, a 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?

The name and title say 'Hunting scouting picks', but the description never states the action verb or the return resource explicitly – it only describes content attributes (access points near 5-10 year old cut blocks and winter ranges, with hunting unit and trail-camera signal). An agent can infer it returns a list of spots, but no sibling (find_spots, check_spot, confirm_spot) is named to disambiguate.

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 real precondition ('Camp Map Pass only') and an explicit scope exclusion (seasons/bag limits not included), which is useful context. However, there is no guidance on when to choose this over nearby siblings like find_spots or check_spot – usage is only implied.

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 readOnlyHint=true and openWorldHint=true, so safety is covered. With no output schema, the description usefully discloses the return fields (bounding boxes, data build time, offline packs), which is exactly the behavioral context an agent cannot get from structured fields here; it still omits pagination, result size, and whether the list is filterable.

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 identifies the resource first, then the returned attributes. There is no filler, hedging, or repetition of the title, and 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?

For a parameterless, read-only listing tool with no output schema and no nested objects, the description supplies the essential return-value information an agent needs to decide whether calling it is worthwhile. It falls short of full completeness only because it says nothing about result volume or stability of the data.

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 description to disambiguate and the baseline of 4 applies. The description correctly implies a no-argument, list-everything call.

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 clear resource (the provinces, territories and states the Camp Map covers) and enumerates what comes back with it, so an agent knows this is a static coverage listing rather than a lookup for a specific place. It does not explicitly distinguish itself from siblings like find_spots or check_spot, but the resource is specific enough that confusion is unlikely.

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 agent can infer this is the tool to call when it needs the map's coverage list, bounding boxes, build dates, or offline pack availability. There is no explicit when-to-use statement, no prerequisites, and no named alternative for related needs such as checking a specific spot.

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 openness and idempotency (openWorldHint, idempotentHint, destructiveHint=false), and the description adds real behavioral detail beyond them: the pending/paid state machine, a retry interval, the 'Authorization: Bearer <key>' usage convention after success, and an activation link. There is a mild tension between the read-only framing ('Checks whether...') and readOnlyHint=false, but the mention of a pass key and an activating link makes clear the call is not purely observational, so this is not a direct contradiction.

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 only two sentences, with no filler. The second sentence is densely packed (nesting the Bearer-header convention and the activation link inside the 'paid' case), which slightly hurts scannability but all content 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?

There is no output schema, so the description carrying the return values (pending with retry interval, paid with pass key, activation link) is necessary and it delivers. It leaves out failure/expiry states (e.g. what happens if payment never completes or fails) and any auth requirement, which are the remaining gaps for a polling tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the single parameter is fully documented in the schema, including its origin ('reference from start_pass_purchase (ag_…)'). The description repeats 'purchase reference' but adds no format or constraint 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?

The description states a specific verb and resource ('Checks whether the payment for a purchase reference has completed') and names the exact outcome states (pending / paid with pass key). Combined with the schema's pointer to start_pass_purchase, an agent can place this tool precisely at the end of the purchase flow and distinguish it from start_pass_purchase and the unrelated marine siblings.

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: it is a post-payment status/collection step ('pending (with a retry interval)' signals polling after start_pass_purchase, and the title says 'after the user has paid'). The description never explicitly names start_pass_purchase as the prerequisite call or states when not to use it, so it stops short of full routing 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 readOnlyHint and openWorldHint, so the safety profile is covered; the description earns its keep by disclosing output shape and behavior not in the annotations: fixed search radii (wildfires within 60 km, road reports within 10 km), result caps (top 3 free, 5 with a pass), and the ordering of heads_up lines first. It does not mention cost, latency, or rate limits for what is a fan-out aggregation call, leaving a small gap.

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 that leads with the user question and then enumerates deliverables in priority order. The embedded list is dense but every clause maps to a real output, so little is wasted; only the wrap-up phrasing (

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a six-parameter composite tool with no output schema, the description does the heavy lifting by enumerating the returned sections and their caps, which an agent needs to interpret results. Remaining gaps (latency, partial-failure behavior when a sub-source is unavailable) are minor given the read-only, open-world annotation profile.

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%, so the schema already documents lat/lng/carrier/radius_km well. The description reinforces that signal is reported per carrier and that nearby-spot results scale with pass status, but adds no syntax, format, or default detail beyond the schema. Baseline 3 for a well-covered 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?

Names a concrete question the tool answers (

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?

'One call that answers ... this weekend' establishes the scenario and implicitly frames this as a consolidation of the narrower siblings (check_spot, weather, wildfires, road_reports, find_spots), which is useful routing context. It never states when NOT to use it or names a sibling explicitly as the alternative, so it stops short of full when/when-not guidance.

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

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

Annotations cover the safety profile (readOnlyHint=false, openWorldHint=true, non-idempotent, non-destructive), and the description adds genuinely non-obvious behavior: the Camp Map Pass key auth requirement, a hard 10-per-day rate limit, and a 'no free text' constraint. It stops short of saying what success/failure looks like or whether the report appears immediately.

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 dense sentence that front-loads the core action, then the accepted values, then authorization and rate constraints. No filler, though the parenthetical enum dump is long and largely duplicative 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?

For a 4-param mutation tool with no output schema, the description covers the essentials: what is stored, what inputs are valid, who can call it, and how often. The only gap is the return behavior/confirmation, which is minor given the low complexity.

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 50%: lat/lng carry their own WGS84 descriptions, while kind and vehicle rely on enums that are already fully self-documenting. The description reproduces the enum values rather than adding meaning, so it neither compensates for nor improves on the schema beyond confirming that only fixed kinds/vehicles are accepted.

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 ('Stores a one-tap field report at a point') and clarifies scope ('the same kind the map's users leave'). It is clearly distinct from read-oriented siblings like road_reports and find_spots, though it never names an alternative outright.

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 context is implied through prerequisites ('Needs the user's Camp Map Pass key') and limits ('at most 10 stored reports a day per key'), but there is no explicit when-to-use this versus check_spot, confirm_spot, or road_reports. The agent must infer that this is the write path for leaving a report.

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 and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context: the data source is user-submitted field reports, the window is fixed at the last 120 days, and the content spans specific categories. However, it does not disclose pagination, rate limits, or the return format.

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 a single front-loaded sentence with no filler. The colon-separated list of report types is somewhat long but directly informs the agent about the data's content, so it 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 simple read-only tool with a fully documented schema and annotations, the description covers the data source, time window, and content categories. Yet with no output schema, it should describe the return structure (e.g., a list of reports with fields) and any pagination or result limits, which it does not.

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 lat, lng, and radius_km are fully documented in the schema. The description adds the implicit meaning that the radius parameter drives the search and that results are always limited to the last 120 days, but it provides no additional syntax or format details 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?

The description clearly states the resource (field reports from map users), the spatial scope (within a radius), and the temporal scope (last 120 days). It enumerates the kinds of conditions reported, which helps distinguish it from a submission tool like report_conditions, though it does not explicitly name that sibling.

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?

There is no explicit guidance on when to use this tool versus alternatives such as report_conditions, find_spots, or camp_map_pass. The description implies usage by describing the returned data, but it offers no conditions for selection or 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 only declare readOnlyHint and openWorldHint; the description adds genuinely useful context: it returns checkout links rather than charging, payment happens in the user's own browser, no account is required, and the returned link is tagged with a purchase reference used to reconcile payment afterwards. This also explains why readOnlyHint is plausible for a 'purchase' tool. It does not cover link expiry or what happens if the tool is called repeatedly.

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 action and then the return-value/mechanism detail. Both sentences carry information (pricing, Stripe, no account, reference semantics) with no filler, though the second sentence is dense.

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 tool with no output schema, the description covers the essentials: what it returns (checkout links), the pricing options, and how the result is used downstream. It leaves minor operational questions open (link lifetime, duplicate calls), which is acceptable at this complexity but not exhaustive.

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 per the rubric the baseline is 4; there is nothing for the description to disambiguate. The pricing tiers mentioned are informational, not 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?

The description gives a specific verb+resource ('Begin a Camp Map Pass purchase') and adds the price/mechanism (CA$55 a year or CA$5 a month, Stripe, no account), so the agent knows exactly what this does. It does not distinguish itself from the closely related siblings camp_map_pass or pass_status, which is the only 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?

Usage is implied by the phrase 'without leaving the conversation' and by the purchase framing, but there is no explicit when-to-use/when-not guidance. Nothing tells the agent how this relates to pass_status (checking an existing pass) or camp_map_pass, so the agent must infer that this is only for users who have not yet paid.

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 this is a non-read-only, open-world, non-idempotent write. The description adds genuinely new context: answers are persisted alongside the forecast that was given, and a Camp Map Pass key is required. It does not address what happens on a stale/duplicate token, which is the main behavioral unknown for a non-idempotent write.

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 dense sentences with zero filler; the storage action and its three answer domains are front-loaded, followed by the persistence note and auth requirement. Nothing is repeated from 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?

For a 4-param write tool with no output schema, the description covers purpose, required token, answer domains, persistence, and auth. The only meaningful gap is error/re-submission behavior on invalid or reused tokens, which an agent would want before calling.

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 only 25% (token only), so the description carries real weight and delivers: it explains token provenance ('followup.token from the plan_trip answer'), gives camped as a yes/no, and lists the signal and road enum values. It adds meaning beyond the raw enum lists, though it doesn't restate field types or which parameters are optional vs required.

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 ('Stores the user's answers') and enumerates the exact three post-trip questions captured. The tie to 'plan_trip (its followup token)' separates it cleanly from ambiguous siblings like report_conditions or road_reports, which are not trip-token-scoped.

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 triggering context ('after a trip planned with plan_trip') and the required artifact (the followup token), so an agent knows when this tool applies. It never names an alternative or a when-not case, though, leaving the boundary with report_conditions/road_reports 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 declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds real behavioral context by disclosing the upstream providers and the geographic routing/fallback logic (EC in Canada, NWS in the US, MET Norway as fallback), but it says nothing about error behavior, latency, caching, or freshness of the data.

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 dense sentence that front-loads what the tool returns before listing providers. Every clause carries information, though the provider list is slightly long relative to its decision value for the agent.

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 does the work of conveying return content and units, and the input schema fully covers the three parameters. It is nearly complete; only the granularity of 'current conditions' and the exact forecast structure are left implicit.

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%: lat/lng units (WGS84, sign convention) and tz_offset_min's default are all documented in the schema. The description adds only output-unit semantics, not parameter meaning, 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?

The description names a specific resource and scope: current conditions plus a 3-day outlook, with the exact returned variables (min/max °C, rain mm, wind km/h). It is clearly distinguishable from siblings like road_reports or wildfires, though it never explicitly contrasts itself with the closest sibling, report_conditions.

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?

There is no when-to-use or when-not-to-use guidance, no prerequisite or limitation stated, and no alternative tool named. The only usage signal is implicit: it takes a lat/lng point, so it is a point-forecast lookup, but that is left for the agent 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?

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuinely useful behavioural context not in the annotations: the coverage is limited to Canada (CWFIS) and the US (NIFC), and results are returned nearest-first. It does not say anything about data freshness or how the results are ordered when distances tie.

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 carrying scope, entities, ordering and provenance with no filler. 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?

There is no output schema, but the description enumerates the returned entity types (hotspots, perimeters, incidents) and the ordering, and the schema fully covers inputs, so an agent can call this correctly. Missing details are minor — data freshness, empty-result behaviour, and result volume.

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%: lat, lng and radius_km are each documented with units, ranges and defaults. The description only echoes the radius concept via 'within a radius', adding no formatting or interpretation 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?

A precise verb+resource statement: 'Active wildfire hotspots, perimeters and incidents within a radius, nearest first.' It names the returned entity types, the geographic scope, the ordering, and the upstream data sources (CWFIS, NIFC), which cleanly distinguishes it from neighbours like weather and road_reports.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the domain — an agent can infer this is the tool for wildfire proximity queries — but there is no explicit when-to-use guidance, no statement of when not to use it, and no alternative tool named for related hazards.

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 supply readOnlyHint and openWorldHint; the description adds real behavioral content beyond them: the paid-pass gating, the ranking factors, and concrete workability thresholds (under 2 mm rain, wind under 35 km/h). It does not mention rate limits or cost per call, but the added context is substantial.

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 leads with the gating condition and then the ranking/output logic, with no filler sentences. It is dense with parentheticals but every clause carries information an 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?

With no output schema, the description carries the burden of describing results and does so: ranked spots plus a 3-day forecast with workable-day flags. Gating and thresholds are covered; only cross-tool routing to the other spot tools 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 schema already documents lat, lng, carrier, radius_km, and tz_offset_min in detail. The description references carrier-based ranking but adds no syntax, defaults, or format guidance beyond what the schema provides; 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 action (ranks nearby spots) and the ranking criteria (carrier signal, Starlink open sky, flat ground) plus the weekly forecast overlay, which distinguishes it from generic siblings like find_spots or check_spot. It never explicitly names what it is not, so sibling differentiation rests on inference.

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 Camp Map Pass paywall implies the usage context (only when the user has a pass), but there is no explicit when-to-use versus find_spots, hunting_spots, or check_spot, and no stated exclusions or prerequisites beyond the subscription. Usage is implied rather than directed.

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