emap — Euskadi hyperlocal mobility

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

No annotations are present, so the description must carry the burden. It discloses that the tool returns neighborhood info, services, and distances, and implies a read-only query. However, it does not mention coordinate format, data scope, or response structure.

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 repeats the same content in three languages, with English appearing last. It is efficient in size but the multilingual rendering adds redundancy without informational 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?

For a simple two-parameter point query, the description adequately conveys the core output. However, without an output schema, it omits return-value details, edge cases, and units, making it minimally complete.

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% and the description never mentions lat/lon, units, or bounds. While the parameter names are self-explanatory, the description adds no semantic detail beyond the raw schema fields.

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 English portion clearly states the tool's purpose: return what is around a point, including neighborhood and nearby services with distances. This differentiates it from nearby_pois, which likely focuses on POI listings, though the verb 'explain' is somewhat generic.

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 no explicit guidance on when to use this tool versus siblings like nearby_pois or search_places. It merely implies a point-based context lookup without stating exclusions or 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?

With no annotations provided, the description carries full burden for disclosing behavior. It only restates the tool's purpose and lists layers; it does not explain how 'nearest' is determined, the output format, error handling, or any side effects. This is a significant gap for a tool with no annotation coverage.

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 English sentence is concise and front-loaded, followed by a necessary list of layers. The multilingual repetition (Spanish, Basque, English) adds redundancy but does not severely harm clarity.

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 and no annotations, the description is incomplete. It does not mention return values, distance units, sorting, or behavior for invalid layers. For a tool with 4 parameters, this leaves significant gaps for an agent.

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 covers 0% in descriptions, but the description compensates for the 'layer' parameter by enumerating valid layer names. However, lat, lon, and limit are not addressed beyond their schema titles, so the compensation is 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 states 'Nearest POIs of a given layer' with a specific verb and resource. It also lists the exact supported layers, which differentiates it from sibling tools like search_places and explain_place.

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 clarifies that the tool works with a specific set of layers, giving implicit context on when to use it. However, it does not explicitly state when not to use it or mention alternatives like search_places.

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 transparency burden. It discloses the straight-line distance limitation, the dataset source (OSM, 2,825 peaks), and the per-candidate nearest stop behavior. It does not detail output structure or any auth/rate-limit concerns, but for a read-only query the key caveat is 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 front-loaded with the purpose, but repeats the same information in Spanish, Basque, and English, which adds no value for an AI agent and makes it unnecessarily verbose. The 'HONESTO' caveat is useful but could be integrated more concisely.

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 at least sketch return values; it only vaguely says 'for each candidate, its nearest stop/station.' Combined with zero parameter semantics, the tool is only partially specified for invocation.

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 does not explain any of the five parameters (lat, lon, min_ele_m, max_results, max_stop_dist_m). It only mentions the general concept of nearest stops, leaving the agent to infer parameter meanings from names/defaults.

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 (Euskadi peaks from OSM, 2,825) and scope (public transport accessibility, nearest stop among 9 networks). It distinguishes from plan_route by noting that plan_route should be used for the actual route, but it lacks a direct imperative verb like 'find' or 'list'.

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 advises using plan_route for the actual foot route to the stop, and warns that distances are straight-line, not walking distances. This provides clear when-to-use and alternative 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?

With no annotations, the description carries the full burden. It discloses useful return information (duration, distance, segments) and a limitation (no complete geometry). However, it omits details about coordinate formats, error handling, or any side effects, though for a read-only routing tool this is somewhat adequate.

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 brief and front-loaded with the core purpose. The multilingual repetition adds some redundancy but is justified for the target audience. It contains no unnecessary 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?

Despite lacking annotations and output schema, the description covers the essential aspects: purpose, modes, and return structure with a key limitation. For a simple routing tool with five parameters, this is fairly complete, though it could mention coordinate system or input format for 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 zero description coverage, so the description must compensate. It adds meaning by enumerating valid mode values (transit, walk, bike, car) and clarifying the tool's point-to-point nature. The coordinate parameters (from_lat, from_lon, to_lat, to_lon) are self-explanatory from their 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 it computes a real route between two points using emap's own infrastructure, and lists explicit travel modes (transit, walk, bike, car). This makes the tool's purpose specific and distinguishes it from plan_hike, though it does not name siblings explicitly.

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 is given on when to use plan_route versus alternatives like plan_hike. The mode list provides some context, but there are no explicit usage scenarios, prerequisites, 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?

No annotations are provided, so the description must carry the full burden. It does disclose a notable behavior: 'honest abstention' when the query is not understood. However, it does not discuss other behavioral aspects like read-only nature, permissions, or error handling, which is acceptable but not exhaustive.

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 in each language, but the three-language repetition (Spanish, Basque, English) is redundant for an AI agent. It front-loads the purpose clearly and avoids fluff, making it efficient despite the multilingual duplication.

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 tool with 4 parameters and no output schema, the description covers the core purpose, input semantics, and a key behavior (abstention). The only notable gap is the undocumented 'k' parameter, which is minor given its default value.

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, so the description must compensate. It explains that lat/lon define the search point and query is the semantic text, but it does not explain the 'k' parameter (number of results). This partial coverage earns a mid-score.

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 performs 'Semantic local search' in Spanish or Basque, returning POIs near a given point. It distinguishes itself from sibling tools like nearby_pois by emphasizing its semantic and multilingual nature.

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 for when to use the tool: semantic queries in Spanish or Basque with a location. However, it does not explicitly mention when not to use it or name alternative tools, so it stops short of full guidance.

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