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

Annotations already mark this as a non-read, destructive mutation, so the description's job is to add nuance beyond that. It discloses the optimistic-concurrency requirement (stale versions rejected), the guarantee that existing orders/invoices are untouched, and that availability is not automatically renewed. This is meaningful context beyond the annotation booleans, though it does not describe failure modes or response behavior.

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?

Three short sentences in ~35 words: what it does, the precondition, and how to reverse it. The primary action is front-loaded, and no sentence repeats data already present in the schema or annotations.

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 mutation tool with no output schema and a destructive annotation, the description covers the essential call-time knowledge: effect, non-effect, version precondition, and renewal mechanism. Minor gaps remain: what the response returns (e.g., a new version number) and whether the paused service becomes invisible to customers in listings.

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 only 25%, so the description must compensate; it enriches exactly the parameter that needed it most by explaining that expected_version must be the current version, implying its role as an optimistic-concurrency token. service_id is self-evident from its pattern and the tool name, and agent_key is already documented in the schema. request_id's role (request correlation/idempotency) is left implicit despite the idempotentHint.

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?

Uses a specific verb ('stop') plus a precise scope: new orders only, explicitly excluding existing orders and invoices. This disambiguates it from siblings like speedbot_exchange_cancel (which would disrupt existing obligations) and the funded-task pause variants, which operate on a different resource.

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?

States a concrete prerequisite ('Requires the current expected_version') and names the recovery path ('Republish with explicit fulfillment consent to renew availability'), implicitly routing to speedbot_exchange_publish_service. What is missing is an explicit when-not, e.g., pointing to cancel for permanent termination versus pause for temporary halt.

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