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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely useful behavior: what the result contains (selected graph, examined alternatives, blockers, search completeness, execution binding), the precise meaning of 'structural cost' (registered graph steps, not runtime/financial/scientific cost), and the caveat that declared facts are validated only at execution. It does not discuss determinism, limits behavior, or failure modes in detail.

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?

Six sentences, front-loaded with the core purpose, then constraints, then return shape, then two clarifying caveats. Every sentence carries information, though the density is high and could be tightened slightly. No filler or restatement of the name.

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 complex planner with nested objects, 0% schema coverage and no output schema, the description does valuable work by enumerating return fields and clarifying cost and validation semantics. The main gap is parameter-level detail (inputs, adapters, constraint fields) that neither schema nor description explains, which matters for a tool with 5 parameters.

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%, so the description carries the burden. It maps loosely onto the constraints object ('Enforce allowed tools, locality, step and search limits') and mentions goals and available contracts by concept, but never explains inputs, adapters (route_durations.v1), or the max_structural_cost/max_search_states semantics. It partially compensates but leaves several nested parameters undocumented in both places.

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 states a specific verb and resource: composing a dependency plan from goal contracts and declared available contracts, with enforcement of tool/locality/step/search limits. It clearly distinguishes planning from execution ('No engines run during planning'). However, it never names or contrasts with the closest siblings such as build_robust_plan, execute_composition, or plan_mission, so the agent must infer differentiation.

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?

Usage is implied rather than stated: the tool is a planning-only step, and the note that no engines run and that arguments are validated at execution hints that execution is handled elsewhere. There is no explicit 'use this when / do not use this when' guidance, nor any reference to alternative planning or execution siblings.

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