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

Goes well beyond the annotations: it names the write side effect (group_field written on every point, default group_id), the destructive consequence of 'replacing any prior color classification' while preserving size/shape channels, the clarification-failure behavior, the 10,000-point ceiling, and the task/return structure. This is exactly the extra context destructiveHint=true alone cannot convey.

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 action and scope, then side effects, then requirements, then the seed variation and return shape. Dense but nearly every clause carries distinct information; the single long paragraph is heavy to parse but not padded.

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 15-param mutation tool with no annotation-level detail beyond flags and a confirmed output schema, the description covers effect, prerequisites, limits and errors well enough to call it safely. The remaining gap is the several unmentioned parameters, which slightly undercuts 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?

With 15 parameters and near-zero top-level schema description coverage, the description carries the burden and covers the important ones well: build_mode values, objective, dwell_time, point_filter syntax with an example, group_field default, seed_point_layer semantics. However ts, ts_handle, metric_fields, map_session_id, expected_revision, group_label_prefix and visit_frequency_field are entirely unexplained, leaving a large undocumented remainder.

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 ('Groups the points of one ingested layer into balanced clusters') and immediately differentiates itself from alternatives by scope: 'with no ZIP or part layer and no territory alignment'. An agent can distinguish it from auto_build, seed_build, direct_build and the part-based tools 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?

Gives clear operating context (ingested point layer only, must supply build_mode/objective/dwell_time 'as in auto_build', missing returns CLARIFICATION_REQUIRED) and scopes the optional seed path. It never explicitly says when to prefer this over auto_build or seed_build, so the routing guidance is inferred rather than stated.

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