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

With no annotations, description carries full burden. It discloses data sources (EONET, GDACS), return format (compact event lists with coordinates), and bbox behavior. Does not mention rate limits or auth, but as a read-only tool this is sufficient.

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 adding value. Front-loaded with purpose, then details. No unnecessary 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?

Given two parameters, bbox filtering combining two sources, and presence of output schema, the description fully covers what the agent needs to know.

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 0%, so description compensates by explaining bbox format as '[w, s, e, n]' and days default of 30. Provides context beyond 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 it returns 'Current natural events and disaster alerts' with optional bbox filter, citing specific sources (NASA EONET, GDACS) and distinguishing from siblings like weather_summary or geocode.

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?

Mentions optional bbox filtering and explains bbox format, but does not explicitly state when to use vs. alternatives or provide 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?

With no annotations, the description carries the full burden. It explains the scene selection strategy (same MGRS tile), computation of expression stats, and output (scenes, means, delta, map_path). It does not mention side effects like file creation but sufficiently describes core behavior.

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 with a summary line followed by elaboration. It is front-loaded with purpose and contains no redundant sentences, making it efficient for an 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?

Given the tool's complexity (7 optional parameters, output schema exists), the description covers the main workflow, output structure, and defaults. It misses edge cases but is adequate for typical usage.

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 0%, so the description must compensate. It explains the RFC3339 format for windows, defaults, and expression default. It adds context about SAME MGRS tile selection and algorithm, though does not detail each parameter individually.

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 compares two time windows over a place and returns matched scenes, index delta, and a swipe map. It uses a specific verb-resource pair and distinguishes from siblings like compute_statistics which likely handles single windows.

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 positions this as solving 'what changed?' and provides default window behaviors, implying use for change detection. However, it does not explicitly state when not to use it or suggest alternatives.

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

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

No annotations are provided, so the description bears full responsibility for behavioral disclosure. It mentions the backend (TiTiler /stac/statistics) and implies a read-only operation, but does not explicitly state read-only nature, authentication needs, rate limits, or potential side effects. This is insufficient given the lack of 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 concise, consisting of three sentences that front-load the purpose. Every sentence adds value: the first states purpose, second explains expression, third mentions AOI and backend. No fluff, though the third sentence could be integrated.

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 6 parameters (3 required) and an output schema. The description covers the core functionality and some parameters, but does not explain the output structure or provide usage patterns beyond the expression example. With an output schema present, the burden is lower, but additional context on return values or pagination would improve completeness.

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 0%, so the description must significantly compensate. It explains the expression parameter with a concrete example and notes the aoi_geojson parameter, but does not describe other parameters like assets, catalog, item_id, or collection_id. The STAC context is implicit, but the assets parameter remains unexplained, leaving gaps.

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 computes pixel statistics (min/max/mean/std/histogram) for a STAC item, with specific mention of band math expression and optional AOI clipping. It distinguishes the tool's purpose from siblings like search_datasets or describe_collection, though not explicitly contrasting.

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 provides context for when to use the tool (computing statistics on STAC items) and mentions optional features like expression and AOI. However, it lacks explicit guidance on when not to use it or alternatives among siblings, leaving some ambiguity.

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 description implies a read operation but provides no additional behavioral context such as permissions, side effects, or error conditions. For a tool with no annotations, this is adequate but minimal.

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?

Single sentence with 10 words, no filler, and front-loaded with the verb and resource. Every word is necessary.

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 is simple with two parameters and an output schema exists, covering return values. The description adequately captures the tool's function, though it could mention that both parameters are required.

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 schema has 0% description coverage, and the tool description does not explain the parameters 'catalog' and 'collection_id' beyond their names. No additional meaning is provided.

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 uses a specific verb 'Get' and clearly states the resource (collection's description, extent, and asset/band layout). It distinguishes the tool's purpose from sibling tools like 'list_catalogs' but does not explicitly differentiate from similar tools like 'preview_item'.

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?

No guidance on when to use this tool versus alternatives. The description does not mention any prerequisites, exclusions, or context-specific usage.

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

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

With no annotations, description fully discloses fallback strategy and return structure (name, lat, lon, bbox, source). Does not mention rate limits or error handling, but output format is clearly specified.

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?

Description is concise (4 lines) with clear sections: purpose, fallback, usage tip, output. Every sentence adds value with no redundancy.

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?

Tool has single parameter and output schema. Description covers all key aspects: purpose, method (with fallback), usage hint, and return fields. Complete for a simple geocoding tool, though error behavior not addressed.

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 0% (no description for 'query' parameter). Description adds guidance to use concise names, but does not specify expected format (e.g., country, commas). Partially compensates but could be more detailed.

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?

Description clearly states the tool resolves a place name to coordinates and bounding box, using explicit verb and resource. No sibling tool performs geocoding, so no differentiation needed.

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?

Provides specific usage advice (use concise names) and explains fallback behavior (Gazet then Nominatim). Could be more explicit about when to use versus alternatives, but siblings do not compete.

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

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

No annotations provided, so description carries full burden. Only states it lists catalogs with descriptions; no mention of caching, pagination, read-only nature, or any side effects. Minimal behavioral 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?

Single sentence with no redundant words. Front-loaded with verb and resource. Efficient and clear.

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?

Given zero parameters and presence of output schema, description is complete enough. It explains what the tool does and adds value by noting it includes what each catalog is good for. Could mention output format but not necessary.

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?

Input schema is empty (0 parameters), so no parameter documentation needed. Description adds no parameter info, which 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?

Clearly states it lists STAC catalogs and their utility. Verb 'List' specifies action, resource is 'STAC catalogs', and adds 'with what each is good for' for extra context. Distinguishes from siblings like search_datasets or describe_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?

Implies usage for discovering available catalogs, but no explicit when-to-use or when-not-to-use compared to siblings. The list of siblings is provided but no guidance on selection.

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

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

No annotations provided, so description carries full burden. It discloses routing to different backends per catalog and optional rescale. Does not mention errors, auth, or destructive effects, but adds useful behavioral context.

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 conveying essential information: purpose, routing, and rescale. No unnecessary words, front-loaded structure.

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?

Tool has 6 parameters and an output schema. Description covers main purpose and routing but lacks details on most parameters. Output schema provides return type, but description should ideally explain key parameters like assets and max_size. Slightly below adequate.

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%. Description only explains rescale with an example. The other 5 parameters (assets, catalog, collection_id, item_id, max_size) are not described, which is insufficient for a tool with 6 parameters.

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 states it provides a browser-openable PNG preview URL for a STAC item. Routes are detailed per catalog (Earth Search, NASA VEDA, Planetary Computer). Distinguishes from siblings like render_map or tile_url_template by focusing on item-level preview.

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?

Does not explicitly state when to use this over siblings. No directives for when not to use or mention of alternatives. Usage is implied but lacks explicit guidance.

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

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

No annotations are provided, so the description carries the full burden. It mentions the HTML is shareable and no server is needed, and describes layer types and compare logic. However, it does not disclose side effects like file overwriting (out_path default null implies temporary file?), permissions, or cleanup. The description gives moderate transparency but has gaps.

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 relatively concise with clear bullet points for layer types. It front-loads the main purpose and uses structured examples. While it could be slightly shorter, every sentence adds value and the organization aids readability.

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?

Given the complexity (6 parameters, 3 required) and no annotations, the description covers the main behavior and layer types. It mentions the return value (file path) but output schema likely exists. However, it lacks guidance for 'bbox' and 'out_path', and does not explain what happens when 'compare' is not set. Completeness is adequate but not thorough.

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 0%, so the description must compensate. It provides detailed structure for the 'layers' parameter (examples of each type) and explains 'compare' behavior. However, it does not describe 'bbox', 'title', 'subtitle', or 'out_path' in any detail. Thus, it adds significant value for some parameters but misses others.

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's purpose: 'Write a self-contained interactive HTML map and return its file path.' The verb 'write' and resource 'interactive HTML map' are specific, and the outcome is clearly stated. This distinguishes it from sibling tools like 'preview_item' or 'tile_url_template' which do not write full HTML maps.

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 provides some usage guidelines, especially for the 'compare' parameter (swipe vs overlay) and explains that item layers auto-resolve. However, it does not explicitly state when to use this tool versus alternatives in the sibling list, such as 'preview_item' for quick previews. The context is helpful but lacks explicit when-not-to-use or alternative comparisons.

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

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

With no annotations, the description carries the full transparency burden. It discloses case-insensitive matching, the specific fields searched, the maximum return count (20), and the response schema. It does not cover pagination, ordering, or empty result behavior, but for a simple search tool the disclosure is fairly comprehensive.

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 three concise sentences. The first sentence states the core purpose, the second adds detail on matching behavior, and the third specifies output. No extraneous words; 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?

Given the tool's simplicity and the presence of an output schema (though not shown), the description covers essential aspects: search scope, matching logic, result limit, and returned fields. It does not mention sorting or relevance, but for a basic search tool the information provided is sufficient for correct usage.

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 0%, so the description must explain parameters. It effectively describes 'keywords' as the search term and 'catalog' as an optional filter: 'across all catalogs or one' implies null means all, string means one. This adds meaningful context beyond the schema's type definitions.

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's purpose: finding dataset collections by keywords across all catalogs or a specific one. It specifies the matching fields (id, title, description, keywords) and the return structure (up to 20 hits with catalog, id, title, summary). This is specific and distinguishes it from sibling tools like search_imagery.

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 when to use the tool (for keyword-based dataset search) and hints at scope (all catalogs or one). However, it does not explicitly state when not to use it or mention alternatives among siblings (e.g., list_catalogs for browsing, search_imagery for imagery). Usage guidance is adequate but lacks explicit exclusions or comparisons.

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

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

With no annotations, the description carries the full burden. It discloses that returns are compact items sorted newest first. It does not mention read-only nature, auth needs, or rate limits, but provides some behavioral context.

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 concise with three sentences, front-loading the main purpose and key parameters. Every sentence adds value without fluff.

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?

Given 7 parameters, 2 required, and no schema descriptions, the description is incomplete. It explains half the params and mentions output usage, but lacks details on catalog, collections, limit, max_cloud_cover. Output schema exists, so returns are covered.

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 0%, so description must add meaning. It explains bbox format, place geocoding, and datetime_range RFC3339. However, it misses limit, catalog, collections, max_cloud_cover. Partial coverage.

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 'Search a STAC catalog for imagery/data items' with specific verb and resource. It distinguishes from siblings like search_datasets and preview_item by mentioning the output can be fed into them.

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

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

It explicitly specifies providing either bbox or place name, and datetime_range format. It also indicates using output for downstream tools. However, no explicit when-not-to-use or alternatives are mentioned.

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

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

With no annotations, the description carries the full burden. It explains the output is a tile URL template but lacks details on error conditions, limitations, or behavior when inputs are invalid. The output schema exists but is not referenced.

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 concise with three sentences, front-loading the main purpose and parameter examples without unnecessary fluff.

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?

Given 7 parameters and 0% schema description coverage, the description only partially explains three parameters. It lacks coverage of required parameters and the role of assets, making it incomplete for an agent to use effectively without additional context.

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 adds meaning to 'expression', 'rescale', and 'colormap_name' by explaining their use in index layers. However, it does not explain the required parameters like 'catalog', 'collection_id', 'item_id', or the optional 'assets' parameter, leaving gaps.

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 that the tool generates an XYZ tile URL template for a STAC item, specifically for web maps. It distinguishes from sibling tools like 'render_map' by focusing on tile URL generation and providing usage examples for index layers.

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 specific usage guidance for index layers with expressions, rescale, and colormap, and notes catalog-specific support differences. However, it does not explicitly compare to alternatives or indicate 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?

With no annotations, the description fully discloses the behavior: it returns daily max/min temperature, precipitation, max wind speed, and dominant wind direction. It explains the wind direction convention (meteorological degrees) and specifies the time range (past_days back and 7 days ahead).

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 succinct with three sentences: the first states the purpose, the second details the output, and the third gives a use case. Every sentence adds value without redundancy.

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?

Given the presence of an output schema, the description adequately covers the tool's functionality, input parameters, and key details like data source. It provides sufficient context for an agent to decide when to use it.

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 0%, but the description adds meaning by explaining the effect of 'past_days' (controls how many days back to include) and implies lat/lon are coordinates. It does not detail lat/lon format but the schema requires them.

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 it provides 'Recent and forecast weather for a point' and lists the specific fields returned (temperature, precipitation, wind speed, wind direction). It distinguishes itself from sibling tools by focusing on weather data.

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 explains that no API key is needed and notes that wind direction is important for smoke, ash, and plume dispersal questions, giving context on when to use this tool. However, it does not explicitly state alternatives or exclusions.

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