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

The description adds valuable context beyond annotations: it discloses antimeridian handling and explains the RFC 7946 convention that minLng > maxLng when a bounding box crosses the antimeridian. With readOnlyHint and idempotentHint already covering safety and repeatability, this extra geometric nuance is the key behavioral disclosure needed.

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 concise sentences that front-load the supported operations and then immediately address the trickiest edge case. No filler; 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 no output schema, a brief note on return values could help, but the description covers the operations, input expectations (lat/lng points), and a critical geometric edge case. It is complete enough for an agent to call the tool correctly without needing more.

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 documents all parameters thoroughly. The description restates the coordinate format and adds antimeridian semantics, but does not add significant parameter-level detail beyond what the schema provides. 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 names three specific geometric operations (point-in-polygon, convex hull, bounding box) on lat/lng points. It distinguishes itself from siblings like distance_matrix or cluster_points by focusing on boundary/geometry operations rather than routing or clustering.

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 through the operation names and the schema, but the description does not explicitly state when to choose one operation over another or provide guidance beyond what's in the enum description. No alternatives 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?

Annotations declare readOnly, idempotent, non-destructive, and the description adds useful behavioral detail: determinism via seeding, date-line safety for centroids, and that DBSCAN noise is returned as a cluster with noise=true. Missing details on output format or pagination, but with annotations covering safety, this is good.

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 front-loaded with the core action and algorithm options, followed by return value details. No wasted 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?

Covers algorithm options, determinism, date-line safety, and noise handling. With annotations covering safety and no output schema, the description could be more explicit about input requirements (e.g., points count) but is largely complete for a clustering 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 all parameters are documented in the schema, and the description only mentions a subset (seeded k-means, epsKm radius). Baseline 3 is appropriate when 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?

States a specific verb (Group) and resource (geographic points) with both algorithm variants named. Clearly distinguishable from siblings like geocode, distance_matrix, or optimize_route.

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 mentions both algorithms and their key parameters (seeded k-means, epsKm for DBSCAN), implying when one might be chosen, but doesn't give explicit guidance on when to prefer k-means vs DBSCAN or when this tool is appropriate versus alternatives. The schema enum description does more of this work.

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/openWorld, so the bar is lower. The description usefully adds the cell cap and the key behavioral distinction that haversine is computed locally while osrm depends on a configured external server, which explains the openWorldHint and implies latency/availability differences.

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 padding. The output shape (rows/columns, units) is front-loaded, followed by the constraint and the mode distinction.

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 carries the return-value burden and does so by naming units (km, minutes) and matrix orientation. It stops short of describing the response structure/ordering or error behavior for oversized requests, but is otherwise sufficient.

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 mode, origins, destinations, and averageSpeedKmh are all fully documented in the schema itself. The description only restates the mode semantics and cell cap, adding no syntax or format detail beyond the structured fields, so 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?

States a specific verb and resource ('compute distances and travel times') plus the exact matrix orientation (origins = rows, destinations = columns). This clearly distinguishes it from siblings like geocode, optimize_route, and cluster_points.

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 the 2500-cell cap and contrasts haversine (local) with osrm (network call), which hints at when each mode applies. However, it never states when to choose this tool over optimize_route or when to omit destinations, leaving usage largely implied.

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 readOnly/openWorld/idempotent/destructive, so the bar is lower; the description adds genuinely new context — the default provider (Nominatim) and a 1 request/second rate limit — which an agent needs to avoid throttling.

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 tightly written sentences with no filler; the mode and provider are front-loaded and the rate limit is appended where it belongs.

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 read-only geocoding tool with full schema coverage, the definition covers modes, provider, rate limit, and even the return shape (lat, lng, display name) despite no output schema. Only minor gaps, such as error behavior on ambiguous addresses, remain.

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 documents each parameter's format, bounds, and forward/reverse applicability. The description adds nothing beyond what the schema states, so the 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?

States specific verbs (forward-geocode / reverse-geocode) and the resource (address or lat/lng), and names the provider. Sibling tools (distance_matrix, optimize_route, cluster_points) are clearly different tasks, so no confusion arises.

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 plus schema makes the mode-selection rule explicit: pass address for forward, lat/lng for reverse. It notes the rate limit, which is operationally relevant, but gives no explicit when-not-to-use or alternative-tool 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?

Annotations already establish readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds some real behavior detail — validation checks structure/coordinate ranges/closed rings, and simplification preserves altitude — but says nothing about output shape, error reporting, or vertex-count effects. Modest added value over the 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 dense sentence with three parallel clauses and no filler; it is front-loaded with the verbs. It is appropriately sized for the tool, though the heavy compression means the parentheticals carry a lot of implicit meaning.

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 four-parameter, multi-operation utility with no output schema and full schema coverage, the description covers all three modes adequately. It omits the return/error format of validate, but that is a minor gap against a read-only, closed-world utility whose safety is already declared.

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 parameters like toleranceKm, points, and geojson are already fully documented in the schema, including units and defaults. The description adds no syntax or format meaning beyond that, so the 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 names three concrete operations (validate, simplify, convert) with specific detail on each — coordinate ranges, closed rings, altitude preservation, and points-to-FeatureCollection. This maps directly onto the operation enum, so an agent can immediately tell what the tool does without opening the 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?

The three operations are enumerated, which implies which one to pick for a given task, but the description never states conditions, prerequisites, or exclusions (e.g. when to prefer simplify over external processing). Usage is inferable rather than stated, and no alternatives are named among the geo siblings.

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, openWorldHint, and destructiveHint false, so the safety profile is covered. The description adds behavioral context beyond annotations: it names the algorithm class (TSP/VRP), explains the distance model ('straight-line distances unless useOsrm is true'), and describes return contents including violations and unassigned stops.

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 are tightly packed with useful information and front-loaded with the core operation. Each sentence earns its place: the first states purpose and constraints, the second enumerates return values, and the third clarifies the distance model.

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?

Although there is no output schema, the description explicitly enumerates the return fields: per-vehicle stop order, arrival/wait/departure minutes, distance in km, time-window violations, and unassigned stops. Combined with a fully described input schema and annotations covering safety, the definition gives an agent enough to call the tool correctly.

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 baseline is 3. The description synthesizes some parameter relationships, such as starting at waypoints[startIndex] and time windows being in minutes after route start, but it does not add significant syntax or format detail beyond what the schema already provides for each parameter.

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: 'Order stops for one or more vehicles (TSP/VRP) starting at waypoints[startIndex]', which clearly identifies route optimization rather than geocoding, distance calculation, clustering, or other sibling functions. It also specifies the algorithm domain and starting constraint.

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 the tool is useful by mentioning optional capacity and time windows, but it does not explicitly state when to choose this over alternatives such as distance_matrix or cluster_points, nor does it provide when-not-to-use guidance. Usage is therefore inferred rather than directed.

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