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

Annotations already declare destructiveHint=true, idempotentHint=false, readOnlyHint=false. The description restates the destructive nature but adds no new behavioral context – no warning about reversibility, cascade effects on related tasks/projects, or auth requirements.

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?

Two short, front-loaded sentences. The endpoint is stated first, followed by the limitation. No waste.

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, non-idempotent operation on a customer that likely cascades to related data, the description is thin. It doesn't mention data loss scope, whether the operation can be undone, or the auth requirements implied by the 7 parameters. Adequate but leaves real gaps.

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 86% and required params (customer_id, confirm) are documented in the schema. The description adds no parameter meaning beyond the endpoint path, so it neither helps nor hurts. 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?

States a specific verb and resource ('Deletes a customer'), plus the exact endpoint. Distinguishable from siblings like archive_customer and restore_customer despite no explicit sibling naming.

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?

No guidance on when to use this versus archive_customer (the reversible alternative) or restore_customer. It notes 'destructive write operation' but doesn't tell the agent to prefer archiving when reversible soft-delete suffices.

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