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

Goes well beyond the annotations: destructiveHint already flags the write, but the description discloses irreversibility, the downstream effect (unmatched price requests stop using the policy), required auth scope, and a concrete failure mode (403 on sandbox keys until workspace is claimed). These are non-obvious operational facts an agent cannot infer from structured fields.

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?

Four short sentences, each carrying distinct information: action, irreversibility, consequence, and two preconditions. Effect is front-loaded ahead of prerequisites, which is the right ordering for a destructive tool.

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?

No output schema exists, but none is needed here — for a delete the agent mainly needs to know it is irreversible, what breaks downstream, and what credentials/workspace state are required, all of which are present.

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 100% and the policy_id description already explains it is the UUID from list_routing_policies, so the description adds nothing about parameters. With a single fully-documented parameter, baseline 3 is appropriate.

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 ("Delete a routing policy") and immediately states the effect on routing behavior ("Price requests that named no function stop using it"). An agent can distinguish this from update_routing_policy or delete_commerce_policy without opening a 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?

Prerequisites are stated clearly (routing write scope, claimed workspace, 403 otherwise), which tells the agent when the call will succeed. However, it never contrasts with alternatives such as update_routing_policy for a non-destructive change, or get_routing_policy to confirm the target first — the core 'when to use this vs. a sibling' question is left implicit.

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