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

With no annotations, the description carries full burden and delivers: it names concrete failure codes (ISOCHRONE_NOT_CONFIGURED, MIXED_BUDGET_TYPES, TOO_MANY_ORIGINS, TOO_MANY_BANDS, PROVIDER_QUOTA_EXCEEDED, BUDGET_OUT_OF_RANGE), quota semantics (fan-out claimed up-front, nothing spent on failure, cap raised by operator), async polling rules (follow _meta.next_action, use sleep_ms not estimated_remaining_ms), and partial-failure behavior (failed_requests[]). It also discloses non-obvious invariants: realign moves parts but never polygons, bands nest and overlap, part assignment is disjoint.

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 'When:' purpose, then organized into labeled blocks (ORIGINS x BANDS, QUOTA, LIMITS, GEOMETRY AND PARTS, Async, Then). Given the complexity it is mostly earned, but it is dense and long enough that some lines (e.g., repeated 'when/when-not' phrasing, scenario-code list) push past necessity.

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-shape explanation is not required, and the description instead supplies the missing operational context: prerequisite key, part_layer requirement, async task flow, error recovery path, and the downstream analyze call. For a high-complexity, high-cost batch fan-out tool, an agent has everything needed to invoke it 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?

With 0% schema coverage across 14 params, the description must compensate and largely does: origins shape ({latitude, longitude, label?} or point-layer reference {point_layer, point_ids?, filter?, label_field?}), bands shape ([{time_budget_seconds}|{distance_budget_meters}] with same-unit rule), travel_mode allowed values, avoid value list, depart_at/arrive_at support, and numeric limits. It leaves tal_id, tal_label, traffic, route_type, part_overlay, map_session_id, and guidance_handle semantically unexplained, which is why it is not a 5.

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+resource: 'draw the area reachable by DRIVING from one or more origins within a time or distance budget', reinforced with concrete synonyms (service area, catchment, coverage ring, reachable range, isochrone, isodistance). It explicitly separates itself from siblings by stating it 'has no objective and does not balance workload' and contrasts with calculate_route and auto_build.

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?

There is an explicit 'When:' clause with example phrasings, plus stated exclusions ('no walking or cycling reachable range, unlike calculate_route'; 'never feed it to auto_build'). Prerequisites (key, part_layer, ts_handle/map_session_id) and follow-up steps (analyze(...), realign) are laid out, so an agent knows exactly when to pick this over alternatives.

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