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

Annotations only flag it as a non-idempotent, destructive write. The description adds rich context beyond that: it discloses the straight-line model with 'no provider calls', that it writes new layers but 'never the source', the exact output layers and fields created, the CLARIFICATION_REQUIRED behavior, and that it returns a task whose result carries coverage_pct/gap counts. This is genuinely additive.

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?

Purpose is front-loaded and nearly every clause carries information (coverage rules, side effects, outputs). It is dense and somewhat run-on with stacked parentheticals, which slightly hurts readability, but for a tool this complex little 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?

Given 16 parameters, an output schema, and destructive write semantics, the description covers the essential workflow: required inputs, the three coverage modes, fallback clarification, created layers, and result shape. It omits meaning for several optional parameters (ts, map_session_id, priority_weights, saturation_threshold), which a complex tool arguably needs.

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 0% across 16 parameters, so the description must compensate. It does explain the semantic core (coverage rule variants, trade with '*' wildcard, gap_territory adding gap ZIPs as one territory), but leaves roughly ten parameters (ts, ts_handle, tier_field, trade_field, demand_metric, capacity_field, map_session_id, priority_weights, contractor_filter, service_zip_field, saturation_threshold) undocumented. Partial compensation, not full.

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+resource: 'Finds coverage gaps in a contractor... network: counts the contractors that reach each demand point.' It also names the sibling it is not ('dividing work is auto_build'), so an agent can distinguish it from auto_build without opening either 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?

It explicitly states the three coverage modes and when each applies (drive_time with max_minutes, drive_time with isochrone_tal, zip_list), the single-trade constraint ('*' for all), and the fallback behavior ('Missing layers, coverage, or trade return CLARIFICATION_REQUIRED'). It also routes the assignment use case to auto_build.

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