kanari wildfires

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

The readOnlyHint and openWorldHint annotations are reinforced and extended by the description. It discloses ranking behavior, time-window defaults, filter semantics, and the meaning of confidence values such as 'corrobore = cross-checked with witnesses', adding real behavioral detail beyond 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?

The description is front-loaded with the core behavior, then filters, then usage examples, then result fields. Every sentence carries useful information without repetition or 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?

The tool has five parameters and no output schema, but the description covers the main calling decisions: time window, spatial filters, result count, ordering, and returned cluster fields. Minor ambiguities like whether filters can be combined and the exact shape of 'position' remain, but these are mostly covered by the input schema.

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 high at 80%, so the schema already documents most parameters. The description adds value by explaining the ranking relevance for `limit`, clarifying the spatial filter options as a group, and stating the default hours window, which helps the agent choose parameters more confidently.

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 action: satellite-detected fire clusters over a time window, with explicit filters and a ranked list of results. It also clarifies the scope ('active... right now') and the returned cluster attributes, distinguishing it from archive or stats 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?

The description gives explicit use-case templates: 'is there a fire near X right now' and 'wildfires in <country> today'. It does not explicitly name alternatives or say when not to use this tool, but the active-vs-archive framing makes the intended context clear.

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 show readOnlyHint=true, so no safety contradiction exists. The description adds valuable behavioral context beyond the annotation: the rolling 72-hour window, the specific comparison being made, and the limitation that emergency-services lead is not covered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loads the core content before adding a clarifying limitation. Every sentence adds information: what is documented, what fields are included, and what the data should not be used for. 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?

For a read-only report tool with one optional parameter and no output schema, the description is complete: it states the time window, the exact comparison, the output fields, and the scope limitation. An agent has everything needed to invoke the tool and interpret its results 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?

The only parameter, limit, is fully specified by the schema with type, default, minimum, and maximum. The description does not add parameter-specific meaning, but for a simple optional pagination limit the schema already provides enough. Schema description coverage is 0%, but the parameter is self-explanatory.

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 exactly what the tool returns: documented cases where kanari's satellite signal preceded the first press article, including place, UTC timestamps, lead in minutes, and median. It also distinguishes the tool's scope from a lead over emergency services, making its purpose unmistakable.

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 explicitly positions this as 'the measured basis for kanari sees fires before the media' and explicitly warns that it says nothing about a lead over emergency services. This gives clear when-to-use and when-not-to-use guidance, even without naming a specific alternative sibling.

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 signal read-only and open-world behavior, and the description adds useful context beyond those hints: the archive starts on 2026-08-03, only significant wildfires are included, and results link to a permanent page URL. It does not discuss pagination or result ordering details, but the annotation coverage lowers the burden on the description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact and front-loaded: it opens with the core search capability, then lists filter dimensions, then gives concrete query examples. Every sentence adds value and nothing is 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 search tool with nine parameters, no output schema, and read-only/open-world annotations, the description gives enough orientation: filter types, output URL behavior, and example queries. Minor gaps remain around the return payload shape and the exact role of limit/order, but the overall definition is functional and not missing critical information.

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 33%, but the description helps compensate by mapping user intent to parameters: 'ISO-2 country' clarifies country, 'date range or month' covers from/to and month, 'minimum detections or power' maps to min_detections and min_frp_mw, and 'status' covers the status enum. It does not explain limit or order, but those have adequate schema-level defaults and enums.

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 ('Search'), a clear resource ('kanari's archive of significant wildfires'), and the key filter dimensions. It distinguishes itself from a live-fire tool by emphasizing 'archive' and the explicit start date, and the example queries make the tool's role immediately identifiable.

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 concrete example queries for when to use this tool: historical fire lookups by country/month, biggest fires, and checking whether a fire is still active. It does not explicitly contrast it with sibling tools like active_fires or fire_details, but the use cases make the intended context reasonably clear.

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?

The readOnly annotation covers the safety profile, so the description only needs to add contextual depth. It lists the record components (timeline, detections per sensor, peak power, aircraft observed, etc.), which goes beyond annotation and tells the agent what to expect.

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 purpose, then provides source context and a colon-separated list of contents. Every clause earns its place; no wasted words.

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 enumerating the expected record components. It is sufficiently complete for a one-parameter read-only fetch, though it does not address potential 'not found' cases or output structure details.

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 0%, so the description must carry the load for the sole parameter. It explains what a slug is and where to obtain it (fire_archive_search or kanari.io URL), though it does not mention the min/max length constraints or error behavior for invalid slugs.

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?

Clearly describes a full record retrieval for archived fires, identified by slug, and lists exact contents. The 'archived' qualifier distinguishes it from active_fires, and the reference to fire_archive_search distinguishes it from the search 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?

States that the slug comes from fire_archive_search or a kanari.io URL, strongly implying when to use this tool: after a slug is obtained. The archived-fire framing gives context, though it does not explicitly exclude active_fires or say when not to use it.

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. The description adds useful behavioral context: data is near real-time, globally scoped, and sparse at night because aircraft fly in daylight. This goes beyond the annotations without contradicting them.

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 concise sentences front-load the core purpose, add a compact list of example aircraft types, then give a practical filter and timing caveat. There is no filler and every sentence 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 no required parameters and no output schema, the description covers scope, freshness, filtering, and likely data availability. It does not describe the exact output fields, but the tool's purpose makes the return type reasonably inferable.

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 explains the country parameter as an optional ISO-2 filter on the aircraft's country of registration, which is not in the schema. The limit parameter is left to its name and schema constraints, so compensation is only partial.

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 identifies the resource: near real-time ADS-B positions of firefighting aircraft, with concrete aircraft types and a worldwide scope. It is distinguishable from the fire-event-oriented siblings, though it lacks an explicit verb like 'list' or 'retrieve'.

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 practical context such as 'worldwide', 'optional ISO-2 filter', and the daylight caveat, which helps an agent know when results are expected. However, it does not explicitly state when to prefer this tool over sibling tools like active_fires or fire_details.

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. The description adds useful context beyond those annotations: the archive source, supported time windows, the 'all since 2026-08-03' bound, and the ready-to-cite sentence with source attribution. It discloses the main behavioral characteristics without contradicting 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?

The description is a single dense sentence that front-loads the core purpose and packs the behavior into a compact list. It has no filler, though the long comma-separated enumeration could be slightly harder to parse quickly.

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 present, the description appropriately enumerates the returned items: counts, peak power, daily series, affected regions, and biggest fires with URLs, plus the citation sentence. It omits the default period of 7d and the precise month-parameter condition, but those are available in the schema.

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 33%, so the description compensates by spelling out period values, the ISO-2 country form, and the worldwide-or-single-country scope. It only indirectly conveys the month parameter's required-when-month relationship and format, which are left to 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 tool returns aggregated wildfire statistics from kanari's archive, with explicit period and geography options, and enumerates the metrics included. This distinguishes it from sibling tools like active_fires or fire_details by emphasizing aggregate, citable figures.

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

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

The description implies use when aggregated statistics or citable figures are needed, and it lists valid period and country inputs. However, it does not explicitly contrast with sibling tools or state when not to use this tool, leaving the decision rule to inference.

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