Check cheaply whether delegating is worth it

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 well: it enumerates what the tool does NOT do (no worker, batch, worktree, or thread; refuses nothing), states the return shape (route solo|either|delegation-plausible, matched rule, provenance, signals, parallel eligibility), and explains the ambiguous return value ('either' means overhead needs justification). It also discloses the 'unknown' bias toward solo, which an agent could not infer otherwise.

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 the negative-behavior list are front-loaded, which is good, but the prose is clause-stacked and repetitive: 'refuses nothing' is restated as 'never refuses', and the advisory/never-required point appears twice. The density obscures rather than compresses, and some of the space spent on repetition could have documented the enum parameters.

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?

Because there is no output schema, the description's explanation of the returned route, rule, provenance, and signals is genuinely necessary and present. However, for a six-parameter tool with zero schema documentation, the complete absence of input-parameter meaning is a material gap that leaves the actual invocation under-specified.

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 six parameters (five of them enums), so the description must compensate and largely does not. It never explains what a 'seam', 'seamSize', 'coreOverlap', 'integration', 'sharedState', or 'verification' value means for routing; only the incidental mention of 'shared contracts' and 'unknown biases advice solo' gestures at the semantics. An agent must guess which enum values push the route toward delegation.

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?

Opens with a specific verb+resource: 'Cheap deterministic check of whether delegating is worthwhile.' That is unambiguous and clearly distinct from the action siblings (delegate_task, delegate_tasks, continue_task) and from explore, since it produces advice rather than action. An agent can classify it without opening the 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 real usage context: inspect cheaply and bounded first, describe candidate leaves rather than the whole objective, defer broad exploration, and treat the result as advisory ('never required', 'choosing zero workers is normal'). It does not name a sibling or give an explicit 'call this before delegate_task' ordering, so it stops short of a 5.

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