emap — Euskadi hyperlocal mobility

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

With no annotations, the description carries the burden of behavioral disclosure. It specifies the type of output (neighborhood, services, distances) but does not mention read-only nature, authentication needs, or any limitations. The description provides sufficient detail for understanding the tool's 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 short and directly states the tool's function. However, it repeats the same information in three languages, which for an English-targeting AI agent adds redundancy without additional value.

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 only two parameters and no output schema. The description gives a reasonable overview of the output content but lacks details on the structure or format of the returned data, which would be needed for full 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?

The schema has 0% description coverage and the parameters 'lat' and 'lon' are not elaborated in the description. No additional meaning beyond their names is provided, such as format, range, or units.

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: providing context about a point including neighborhood and nearby services (rail, bus, toilets) with distances. It effectively differentiates from sibling tools like nearby_pois (which likely focuses on POIs) and plan_route (navigation).

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 for exploring a place's surroundings but does not explicitly state when to use it versus siblings or when not to use it. There are no exclusions or alternatives 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 full burden. It does not disclose behavioral traits like distance calculation, ordering, pagination, or result limits. Simply says 'Nearest POIs' without further detail.

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 repeats same content in three languages, making it verbose. Could be condensed to one sentence. Front-loading is partial but redundancy hurts conciseness.

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, no annotations, 0% parameter coverage. Missing essential context like distance units, sorting, output format, and error handling for a 4-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 description coverage is 0%, yet the description only lists layer values, ignoring lat, lon, and limit. Baseline 3 for full coverage, but here description adds minimal value beyond parameter names.

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 finds nearest POIs for a given layer, listing available layers in three languages. It distinguishes from sibling tools like search_places by specifying 'nearest' and 'given layer'.

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 explicit guidance on when to use this tool vs alternatives (e.g., search_places, plan_route). The description implies usage for retrieving nearest POIs but does not provide context for exclusion or comparison.

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 honestly discloses that distances are straight-line, not walking routes. No other behavioral traits (e.g., rate limits) are mentioned, but the core limitation is transparently communicated.

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 reasonably concise but includes redundant multilingual text. It front-loads the core purpose but could be streamlined by focusing on one language or breaking into structured sections.

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 description is incomplete for the tool's complexity (5 parameters, no output schema, no annotations). It fails to explain input parameters beyond lat/lon, describe the output format, or clarify the scope of the 9 networks.

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 minimal parameter meaning beyond the schema. It implies lat/lon are the hike start location but does not explain min_ele_m, max_results, or max_stop_dist_m. With 0% schema coverage, this is insufficient.

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 identifies Basque Country peaks reachable by public transport, listing the nearest stop/station. It distinguishes itself from sibling plan_route (actual routing) but could more explicitly state the geographic restriction.

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 states when to use (finding peaks by public transport) and advises using plan_route for the actual walking route. It names a clear alternative (plan_route), fulfilling the when/when-not/alternatives criteria.

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 provided, the description carries full burden. It notes that returned segments lack full geometry, which is helpful, but does not disclose rate limits, permissions, or error 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 short but includes the same information in three languages, adding redundancy. Core info is present but could be more streamlined.

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 no output schema, the description mentions returned fields (duration, distance, segments without geometry). However, for a routing tool, missing context includes whether waypoints, traffic, or departure time are supported.

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%. The description only lists mode values (transit, walk, bike, car) but does not explain format, units, or constraints for lat/lon parameters. It adds minimal value over parameter names.

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 'Real route between two points' and lists return fields (duration, distance, segments). It names the infrastructure (OSRM/OTP) and available modes, distinguishing it from siblings like plan_hike.

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 lists modes (transit, walk, bike, car) but does not explicitly state when to use this tool over alternatives like plan_hike or search_places. No prerequisites or exclusions 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?

No annotations are provided, so description carries the burden. It discloses 'honest abstention' if query not understood, which is helpful. However, it lacks details on authentication, rate limits, or error handling.

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 compact and multilingual but slightly repetitive. Each language version restates same info; could be more concise but still efficient.

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 no output schema, description covers main functionality and abstention behavior. Missing explanation of output format and 'k' parameter, but sufficient for basic tool understanding.

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 has 0% description coverage. Description clarifies 'query', 'lat', 'lon' but does not explain 'k' (integer, default 5) which likely controls result count. This is a gap.

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 performs semantic local search in Spanish or Basque, returning POIs near a point. It distinguishes from siblings like 'nearby_pois' by specifying semantic query and language constraints.

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?

Implied usage for semantic/local queries in Basque/Spanish, but no explicit when-not-to-use or mention of alternatives like nearby_pois for non-semantic searches.

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