Cluster points

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.