SkyddsrumsKollen — Swedish Civil-Defence Shelters

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds substantial behavior beyond that: limit clamping (1-25, default 10, floors fractions, echoes effective limit), output fields (address, capacity, distance), the absence of a municipality field, and the no_coverage response for out-of-range coordinates. No contradiction with 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 paragraph of about 120 words, with the core purpose front-loaded and each subsequent sentence providing necessary detail or a caveat. The closing emergency note is slightly tangential but still useful; the density is high but not wasteful.

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 rich annotations and presence of an output schema, the description still adds all invocation-relevant information: parameter behavior, coverage bounds, no_coverage status, and an explicit alternative sibling. An agent can correctly select and call the tool without further clarification.

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%, but the description enriches the parameters by explaining the limit default and floor/echo behavior and by clarifying the effective coordinate bounds for lat/lng. It also adds semantic context that the address serves as the location identifier since there is no municipality field.

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 opens with 'Find the nearest Swedish civil-defence shelters (skyddsrum) to a WGS84 position, sorted by distance' — a specific verb, resource, and ordering. It also explicitly names search_location as an alternative for place-name input, distinguishing it from at least one 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?

Explicitly instructs 'Use search_location first if you only have a place name', giving a clear when-to-use vs when-not-to-use condition. It also states Sweden-only coverage and the resulting 'no_coverage' status for out-of-range positions, which helps agents decide whether to call 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 already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is set. The description adds important behaviors beyond that: the found=true/false semantics, that found=false is a successful response, and that a malformed id triggers an INVALID_ARGUMENT error. This substantially enhances transparency beyond structured 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?

A single, information-dense sentence that front-loads the purpose and weaves in all critical details (id source, return fields, success and error cases) without any fluff. 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?

Even though an output schema is not provided in the given definition, the description fully explains the return values (found flag, address, capacity, coordinates, page URL) and error behavior. For a simple one-parameter read-only tool, nothing an agent needs to invoke it correctly is missing.

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

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

Schema description coverage is 100%, with the parameter fully documented: 'Shelter id (UUID) from find_nearby_shelters, search_shelters or a skyddsrumskollen.nu URL.' The description mostly reiterates this source information without adding new semantic value. Baseline 3 is appropriate because the schema does the heavy lifting and the description adds minimal extra meaning.

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

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

The description states a specific verb ('Get details') and a precise resource ('one Swedish civil-defence shelter') identified by its SkyddsrumsKollen id. It also distinguishes itself from sibling search tools by clarifying it is a direct fetch by id, and it enumerates the returned fields. This is unambiguous and differentiates it from find_nearby_shelters and search_shelters.

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 implicitly tells when to use this tool: when you already have a shelter id from a previous tool result or from a skyddsrumskollen.nu URL. It does not explicitly name sibling tools or exclude them, but the context is clear. A named alternative would push this to 5.

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 mark this as read-only, idempotent, non-destructive, and open-world. The description adds meaningful behavioral context by specifying what data is returned, notably the 'last synced from MSB' timestamp, which signals freshness and dynamic data. No hidden side effects or safety concerns remain undisclosed.

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 compact sentence that front-loads the operation and scope, then adds three concrete data points. Every clause earns its place; there is no filler or repetition of the schema or annotations.

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, a complete output schema, and safety profile fully covered by annotations, the description provides all needed context. It even addresses dataset freshness, and the sibling list confirms the tool's niche as national aggregate stats.

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

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

The tool has zero parameters, so there is no parameter behavior the description must explain. Baseline for zero-parameter tools is 4, and the description appropriately focuses on the output rather than parameter semantics.

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 resource ('national statistics for Sweden's civil-defence shelters'), and enumerates the exact returned values: total registered shelters, total capacity, and last sync time. This clearly distinguishes it from sibling tools like get_shelter or search_shelters, which target individual shelters or searches.

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 'national statistics' wording makes it clear this is for aggregate overview rather than individual shelter lookup, providing usable context alongside the sibling tool names. It does not explicitly state when not to use it or name an alternative, but the scope is self-evident enough for correct 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds valuable behavioral details beyond annotations: it uses OpenStreetMap Nominatim, is limited to Sweden, and returns up to 5 candidates with name, lat, and lon. This gives the agent a realistic expectation of external dependency and result limits.

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 with no filler: purpose, external source and scope, result count and fields, and a direct downstream usage instruction. Every sentence earns its place and the key limitations are front-loaded.

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

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

For a single-parameter read-only tool with full schema coverage, annotations, and an output schema, the description covers all necessary operational details: geographic scope, external service, result format, and a usage path. Nothing critical is missing.

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

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

Schema coverage is 100%, and the schema already provides a clear description and examples for the query parameter. The tool description adds the context that query can be a city, town, or street address, but this mostly restates schema content rather than providing new semantic depth. 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 description clearly states the tool searches for a Swedish place and returns matching coordinates, with a specific verb and resource. It distinguishes itself from sibling tools like search_shelters by focusing on geographic locations, not shelters.

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 clear context: it searches Swedish places and explicitly instructs to use the resulting coordinates with find_nearby_shelters. It does not explicitly exclude alternatives, but the downstream usage guidance is sufficient for correct 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?

Annotations already cover read-only, idempotent, non-destructive behavior, so the description adds valuable context beyond that: accent-insensitive substring matching, the fact that matches are verified as actual substrings, and the return behavior (total_matches, total_is_exact flag when count is a lower bound, ordering by largest shelters, limit flooring and echoing). No contradictions with 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 dense but every sentence earns its place: the core purpose is front-loaded, followed by matching semantics, a critical exclusion with alternatives, and return behavior. No filler or redundancy; it is as concise as needed for the information conveyed.

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 modest complexity (2 params, output schema present, annotations covering safety), the description covers everything needed for correct invocation: input type, matching rules, dataset limitations, routing to alternatives, and what the response contains (total_matches, total_is_exact, ordering, limit behavior). The presence of an output schema covers return details, so nothing essential is missing.

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

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

Schema description coverage is 100%—both 'query' and 'limit' are well-described in the schema with examples and constraints. The description reinforces these but does not add significant new meaning beyond the schema; it merely restates the address nature of 'query' and the limit behavior already in the schema. Baseline 3 is appropriate as the schema does the heavy lifting.

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

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

The description clearly states it 'Search(es) Swedish civil-defence shelters by ADDRESS text' with explicit examples of street names and property designations. It also explicitly distinguishes from siblings by noting it cannot list shelters in a town, which differentiates it from search_location and find_nearby_shelters.

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 when-to-use guidance: it is for address-based lookups, and it explicitly says 'for shelters in <place> use search_location + find_nearby_shelters instead.' It also clarifies a dataset limitation (no municipality/city field) that prevents certain queries, leaving no ambiguity about alternatives.

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