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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds that results are plotted onto a 'shareable verification map', which hints at a persistent side effect not captured by the annotations, but it says nothing about Overpass timeout behaviour, query failures, or how many hotspots are retained.

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?

Two sentences, front-loaded with the core action (query + H3 binning) before the secondary output behaviour (hotspot plotting). No filler or redundant restatement of the name.

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?

An output schema exists, so return values need not be explained, and the oneOf location/bbox exclusivity is handled structurally by the schema. What remains thin is operational context around failure modes and the nature of the plotted map output, but overall the description is adequate for a seven-parameter read 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 100%, so every parameter including query, resolution, bbox/location, radius_meters, timeout_seconds, and use_area_boundary is already documented in the schema. The description only echoes that resolution drives the binning and adds no format or default guidance beyond what the schema states.

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 two concrete operations: executing an Overpass query and binning results into H3 hexagons at a resolution, plus plotting density hotspots. This is a specific verb+resource statement an agent can act on. It does not explicitly contrast with the sibling search_overpass or get_h3_indices, so differentiation is left implicit.

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?

Usage is only implied: the tool is for spatial density analysis rather than raw feature retrieval. There is no explicit statement of when to pick this over search_overpass (raw results) or get_h3_indices (index retrieval), and no prerequisites or exclusions are given.

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=true, idempotentHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description goes beyond them with real operational detail: an external provider dependency (FOSSGIS/OSRM, overridable via OSRM_API_URL), a hard rate limit of max 1 req/s, and the side effect of drawing the path on the verification map. It stops short of describing failure behavior when a provider is unreachable or a place name fails to resolve.

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?

Two sentences, front-loaded with the capability and outputs before the provider/rate-limit detail. Dense with little waste, though the trailing parenthetical about OSRM_API_URL and the map-drawing clause are secondary information that could be split or subordinated more cleanly.

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 an output schema present, the description need not explain return values, and it correctly focuses on capability, data source, rate limits, and side effects. The main remaining gap for a 4-parameter open-world tool is failure and resolution behavior (what happens when a place name is ambiguous or the routing service errors), which the description leaves silent.

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%, including per-parameter docs for origin/destination formats, the profile enum, and return_steps, so the schema does the heavy lifting. The description adds only the notion that endpoints can be coordinates or place names and that turn-by-turn output exists, without adding format or edge-case detail beyond the schema. Baseline 3 applies.

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 a specific verb and resource — 'Calculate real-world travel distance, duration, turn-by-turn summary, GeoJSON route geometry, and route bounding box' — and scopes it to 'between two locations or coordinate pairs'. It enumerates the outputs so an agent knows exactly what it gets, and no sibling tool (get_bounds, spatial_calc, search_overpass) covers routing, so the resource is unambiguous.

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?

Usage is only implied: the phrase 'between two locations or coordinate pairs' hints at routing use cases, and the rate-limit note constrains call frequency, but there is no explicit when-to-use, when-not-to-use, or pointer to an alternative sibling (e.g. spatial_calc for straight-line distance, reverse_geocode for resolving place names). An agent must infer the routing niche itself.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine context by identifying the output as a link into an external visual Bounding Box tool, which the annotations do not convey. It stops short of saying whether the URL is persistent, shareable across users, or has any length/expiry limits, which is the main behavioral question for a link-generating tool.

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?

Two short sentences, front-loaded with the purpose before the input-format details, with no filler. Minor waste: the format enumeration duplicates the bbox schema description almost verbatim, so the second sentence earns less than its length suggests.

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 a full output schema and complete annotation coverage, the description supplies what structured fields cannot: the destination and visual purpose of the generated URL. It leaves only secondary details (URL lifetime, sharing scope) unstated, which is a small gap rather than a blocking one.

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% and the bbox parameter already enumerates the same accepted formats (raw lat/lng string, WKT, GeoJSON, tile z/x/y, ogrinfo extent). The description's second sentence largely restates that list without adding parsing rules, precedence between formats, or how ambiguous strings are disambiguated, so baseline 3 is correct.

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 verb and artifact ('Generates a URL') plus the target ('visual Bounding Box tool to display these coordinates on a map'), which makes the outcome concrete. No sibling tool (get_bounds, spatial_calc, reverse_geocode, etc.) produces a shareable visualization link, so the agent can separate this tool from the rest of the family without opening a schema.

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?

Usage is implied rather than stated: 'display these coordinates on a map' hints the tool is for visual verification of a geometry, and the formats list hints at acceptable inputs. There is no explicit when-to-use/when-not, no statement of prerequisites, and no named alternative for cases where a machine-readable geometry is needed instead (e.g. get_bounds).

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 safety (readOnly, idempotent, non-destructive) and openness, so the description's job is narrower and it delivers: it discloses the external dependency on Nominatim with configurable Photon/Mapbox fallbacks, and that unknown EPSG codes are auto-fetched from epsg.io — both network-facing behaviors an agent should know about. It does not mention latency, rate limits, or failure behavior when the geocoder misses.

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 front-loaded sentence that leads with the primary capability and the two input modes, then the format list. It is dense and slightly run-on, and the format enumeration duplicates the bbox schema, but no sentence is wasted.

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?

An output schema exists, so return values need not be explained. Given the input schema, annotations, and output schema, the description supplies the remaining essentials: the external geocoding providers, the projection-source fallback, and the accepted geometry formats.

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%, so baseline is 3. The description restates the bbox input variants and 'optional metric buffering' (buffer_meters), but adds no syntax, defaults, or edge-case guidance beyond what the property descriptions already say; epsg, zoom, format, precision, and coord_order are untouched.

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?

States a specific verb and resource ('Get converted coordinates') and names the two input modes it handles: a bounding box or a natural-language location search. An agent can tell this is a coordinate-conversion helper rather than a geocoder or route tool, though it never names a sibling (e.g. reverse_geocode) to draw the boundary 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?

Usage is only implied: the enumerated input formats (WKT, GeoJSON, ogrinfo extent, z/x/y tiles, 'lat,lng', raw strings) suggest when the tool fits, but there is no explicit 'use this when…' or 'use reverse_geocode instead when…' routing. With nine siblings including reverse_geocode and spatial_calc, the overlap remains for the agent to infer.

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 the safety profile (readOnly, idempotent, non-destructive, open-world), so the description is free to spend its words elsewhere — and it does: it discloses the licensing/auth constraint (free for non-commercial, paid key or self-hosted ELEVATION_API_URL otherwise) and, more importantly, that grid results are point-sample statistics, not guaranteed true extrema or slope. That caveat materially affects how an agent reports results. It doesn't mention rate limits or failure behavior for out-of-coverage coordinates.

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?

Two dense sentences, front-loaded with the core action and units before the licensing and sampling caveats. The nested parentheses are slightly heavy but every clause carries information the agent needs; nothing is 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?

An output schema exists, so return values need no explanation, and annotations carry the safety profile. The remaining gap is precedence: all four parameters are optional with three mutually alternative entry modes (points, bbox, location), and the description never states what happens if more than one is provided or what the fallback is — a real ambiguity for a zero-required-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 coverage is 100%, so the schema already documents every parameter, which sets the baseline at 3. The description adds only the mode relationship (grid_size applies to bbox sampling) and the statistical meaning of those samples; it says nothing extra about how 'location' is resolved or what happens when multiple mode parameters are supplied together.

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?

States a specific verb+resource with units and data provenance: 'Query terrain elevation in meters above sea level using the Open-Meteo 90m Copernicus DEM API', and names both operating modes (point coordinates vs N×N bbox grid). It doesn't explicitly contrast itself with any sibling, but none of the listed siblings (get_bounds, reverse_geocode, spatial_calc) overlap with elevation lookup, so misrouting risk is low.

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 'OR' framing tells the agent that point queries and grid sampling are alternative modes, and the parenthetical warns when grid sampling is the wrong basis for area-wide min/max/slope claims — genuine when-not guidance. It stops short of saying how to choose among the three entry parameters (points vs bbox vs location) or which takes precedence.

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 read-only, idempotent, non-destructive, and open-world behavior. Beyond that, the description usefully discloses that polygon and named-location inputs fill exact geometry including interior holes rather than only the bounding rectangle, which is relevant 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 two front-loaded sentences with no filler. The core operation comes first, followed by the important geometry detail.

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 seven parameters but full schema coverage, an output schema, and rich annotations. The description covers the core operation and the key polygon-hole behavior; only sibling differentiation is notably absent.

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%, so the schema already explains bbox, location, resolution, compact, summary_only, return_geometry, and use_polygon_boundary. The description reinforces the polygon-versus-bbox behavior but adds little parameter meaning beyond 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 states a specific verb and resource: get Uber H3 cell indices for a polygon, location boundary, or bounding box at a target resolution. It clearly identifies the operation but does not differentiate this tool from siblings such as aggregate_overpass_h3 or get_bounds.

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 usage by naming accepted geometry inputs and the target resolution, so an agent can infer when the tool applies. However, it gives no explicit when-to-use versus alternatives guidance or exclusions for sibling tools.

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 read-only, idempotent, open-world and non-destructive, so the safety profile is covered. The description adds real context beyond that: results come from a built-in category index with a live Taginfo API fallback, telling the agent to expect external network-dependent lookups and that this is the sanctioned source of tag truth.

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?

Two sentences, zero filler, with the tool's role and its data sources front-loaded. Nothing is repeated from the annotations or 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?

An output schema exists so return values need not be explained, and annotations carry the safety profile, leaving a simple one-parameter lookup. Minor omissions remain: behavior when a category is unknown, and whether the live API fallback affects latency or result variance.

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?

With 100% schema description coverage and a single required parameter already exemplified in the schema ('food', 'ev charging', etc.), the schema does the work. The description only reinforces breadth ('any category') without adding format, matching, or normalization guidance beyond what the schema states.

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 gives a specific verb and resource: look up OpenStreetMap tags for a category, framed as a 'discovery tool'. That role contrasts implicitly with siblings like search_overpass (which runs queries) and reverse_geocode, though no sibling is named outright.

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?

'For any category' implies the call context, and the anti-hallucination framing hints it should precede tag-dependent queries. There is no explicit when-not-to-use clause and no named alternative tool to route to instead, so the agent must infer the workflow position.

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 readOnly, idempotent, openWorld, and non-destructive, so the safety profile is covered. The description adds only the shape of the returned data, which is largely redundant with the existing output schema, and says nothing about rate limits, coverage gaps, or fallback behavior when no feature is found.

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 front-loaded sentence with the verb and resource first, then the output summary. The enumeration of return fields is slightly padded given an output schema already exists, but nothing is confusing or wasted.

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?

Parameters are fully documented, annotations cover the safety profile, and an output schema exists, so the description need not explain return values. The main remaining gap is sibling differentiation, which matters here because search_overpass and get_bounds operate near this query space.

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%, including coordinate ranges and the zoom scale (0=country to 18=building/address). The description mentions only lat/lng and adds no meaning beyond the schema, so the baseline of 3 applies.

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?

States a specific verb and resource ('Reverse geocode latitude and longitude coordinates') and enumerates what it yields (place name, address components, OSM details). It is clear on its own, but it never distinguishes itself from siblings like search_overpass, which could also answer a 'what is here' question.

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 parenthetical 'what is here?' implies the query type this tool answers, giving implicit usage context. There is no explicit when-to-use statement, no prerequisites, and no routing to alternatives such as search_overpass for tag-based lookups.

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 readOnly/idempotent/openWorld/non-destructive, yet the description still adds substantive behavior: the server wraps the query in spatial filters, detects Overpass runtime errors, and returns provenance, completeness metadata, distance calculations, and a map link. The note that the query is auto-wrapped with spatial filters materially changes how an agent should construct input.

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?

Front-loaded with purpose and scope, then organized under two clear headers, with no filler sentences. The eight common tag examples are useful for syntax learning but become repetitive after the first three, which all follow the same nwr["key"="value"] pattern.

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 an 11-parameter, open-world query tool with a full output schema and complete annotation coverage, this is close to complete: modes, query construction rules, count fast-path, and return content are all covered. Minor gaps remain around pagination behavior across pages and what a partial/failed query looks like to the caller.

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%, so the baseline is 3, but the description adds real meaning: the 'DO NOT include spatial filters or output directives' constraint on query, the '2km → 2000' unit interpretation for radius_meters, and the note that sort_by_distance is on by default for circle mode and point locations. The tag examples also teach valid Overpass QL syntax that the schema only gestures at.

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 first sentence gives a specific verb and resource ('Execute an Overpass QL query to find POIs, roads, or other OSM features') plus the three supported spatial scopes. It is unambiguous what the tool does, but it never explicitly distinguishes itself from the closest sibling, aggregate_overpass_h3, which presumably wraps the same data source for H3 aggregation.

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 SEARCH MODES block gives clear conditional routing among location, bbox, circle, and count_only, and radius_meters carries an explicit 'use ONLY when explicit distance is specified' exclusion. What is missing is any guidance on when to prefer a sibling tool (e.g. aggregate_overpass_h3 for aggregation, list_osm_tags for tag discovery) over this raw search.

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 readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuine behavioral context beyond them: deterministic results, no network access, interior holes respected in containment tests, and grid bounds of 1-20 with default 2. It does not describe failure modes for malformed WKT or out-of-range rows/cols, but the added disclosure is substantive.

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?

Front-loaded with the core purpose, then a single structured enumeration of the four operations. Dense with parenthetical detail but nearly every clause carries operational information; the one-sentence mega-structure is slightly harder to scan than a short bulleted layout would be.

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 an output schema present, return values need no explanation, and all four operation modes plus their parameter roles are covered. What remains thin is edge-case behavior (invalid geometry input, behavior when bbox_a is a polygon for split_grid), which keeps it just short of fully complete for a six-parameter multi-mode 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 coverage is 100%, so baseline is 3; the description earns above it by clarifying geometry formats the schema leaves generic ('bbox or WKT/GeoJSON polygon', 'lat,lng' origin/destination) and by tying cols/rows to the split_grid subdivision semantics. The mapping of which parameter is consumed by which operation is spelled out in prose as well as 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?

States a specific verb and resource ('deterministic offline geometric calculations on bounding boxes, points, and polygons') and then enumerates the four operations with their outputs (overlap area %, union & intersection bbox, Haversine distance, N x M grid). The 'zero network calls' clause separates it from network-dependent siblings like reverse_geocode and search_overpass.

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?

Each operation name is paired with the condition that selects it (use 'relation' for two-geometry comparison, 'point_in_geometry' for point-in-polygon with holes, 'distance_bearing' for point pairs, 'split_grid' for chunked queries), which is effectively mode-selection guidance. It stops short of naming an explicit sibling alternative or stating when not to use it, so it is clear context rather than full when/when-not routing.

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