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

With no annotations, the description carries the full burden and does so: it declares read-only, deterministic, static-state-machine behavior that 'executes nothing', describes the return payload (next_tool, drafted next_args, missing_inputs, blocked_by, remaining_steps, guidance inlined), and names the enforced invariants (mc_first, viewer_before_compute, build_after_ingest, conditional analysis_freshness) plus the 'never invents a budget' guarantee.

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 and 'When:' are front-loaded, which is good, but the bulk of the description is a single dense run-on parenthetical enumerating every category, state key, and input, which is hard to scan. The content earns its place but the structure is not well-segmented.

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 routing/advisor tool with an output schema and a stateful multi-step contract, the description is complete: it covers prerequisites, per-category inputs, enforced ordering invariants, return fields, fallback behavior, and even scenario tags. Nothing an agent needs to invoke it correctly is missing.

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 coverage is 0% with no enums, so the description must compensate and does: it enumerates valid intent_category values (builds, edits, map overlay, routing, reachable areas, scheduling), lists the agent-supplied state keys per category, and details optional inputs including aliases and conditional requirements for each category.

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 role ('deterministic read-only next-action advisor for multi-step workflows') with a clear verb and resource, and explicitly distinguishes itself from siblings like discover_intent and the concrete action tools it routes to (isochrone_build, schedule_visits, load_part_layer). An agent can tell immediately this is a planning/orchestration tool, not an executor.

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?

Explicit 'When:' clause states the triggering condition (you know the intent and want the validated next call instead of guessing order), names discover_intent as the prerequisite alternative when intent is unknown, and prescribes re-calling after each completed step. It also documents the fallback for unsupported categories, leaving little to inference.

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