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

Annotations already flag destructiveHint=true, so the irreversibility claim is consistent rather than contradicting, and the description adds value the annotations do not carry: the action cannot be undone by another tool, plus the auth and workspace-claim requirements with the 403 outcome. This is exactly the extra behavioral context destructive operations need.

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?

Front-loaded with the action and argument, then the caution, then the two gating requirements. Every sentence carries distinct information with no repetition.

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 destructive, single-parameter tool with no output schema, the definition covers what matters: irreversibility, how to verify the target, and both access prerequisites. No output-schema explanation is needed since none exists.

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 100% and the single parameter is fully documented in the schema ("The customer: its id, as list_customers shows it"), so the description adds nothing beyond "pass customer_id." Baseline 3 applies when the schema does the heavy lifting.

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?

States a specific verb and resource ("Delete a customer") plus the required argument, and contrasts the operation with get_customer, which is the natural sibling check. An agent can distinguish this from update_customer or delete_contact 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?

Gives explicit when-to-use context (delete vs. verify with get_customer first) and names two prerequisites—a claimed Last Price credential and a claimed workspace—including the concrete failure mode (403) for self-registered sandbox keys. Nothing is left to inference about gating conditions.

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