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

With no annotations provided, the description carries the full burden. It discloses important behaviors: it selects the least-burden route, considers multiple constraints, supports optional baselines, and may produce a no-work decision with no claimed result. It also promises a hash-bound decision receipt. These are meaningful behavioral details beyond the simple action of routing.

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?

The description is four sentences, front-loaded with the core purpose, and each sentence adds distinct value: what it does, constraints, optional baselines, special decision case, and return behavior. No redundant or filler content.

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 tool with no annotations, a minimal schema, and an output schema, this description is quite complete. It covers purpose, key inputs, behavioral nuances, and output. It does not elaborate on request_id, but that parameter has a default and is likely incidental. The mention of a decision receipt and no-work scenario covers potential ambiguity.

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%, and the description does not explicitly describe the 'task' or 'request_id' parameters. However, it does mention specific fields within the task object ('allow_defer/value/urgency') and 'optional baselines,' which gives some semantic meaning to the otherwise generic task object. This partial compensation justifies a middle score.

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 clearly states the tool's purpose: 'Choose the least-burden eligible route for a task.' It specifies the verb 'choose' and the resource 'route for a task,' and lists hard constraints that distinguish it from siblings like 'best_next_steps' or 'compute_efficiency_report.' This is a specific, non-tautological statement.

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?

The description implies when to use the tool: when a task must be routed based on constraints like quality, cost, latency, etc. It does not explicitly name alternatives or exclusion criteria, but the context is clear and no misleading guidance is given. It also mentions special cases like 'allow_defer/value/urgency' fields leading to a no-work decision, which further clarifies usage.

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