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

With no annotations, the description carries the full burden and covers key behavioral aspects: it discloses the required permission ('crm:write'), the error behavior for missing or foreign IDs ('answers 404'), and a domain-specific nuance about consent residing in the 'marketing' sub-resource. This goes beyond the schema and adds meaningful context, though it doesn't detail side effects or idempotency.

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 concise and well-structured: it opens with the core purpose, then delivers critical operational details (permission, error behavior, consent caveat) in just four sentences. No filler or redundancy, and it front-loads the most important information.

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 simple delete operation with two parameters and no output schema, the description covers the essential operational context: purpose, permission, error handling, and a relevant domain rule. It doesn't address potential side effects or reversibility, but given the simplicity, it is reasonably complete.

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?

The schema provides descriptions for both parameters, but they are just the parameter names ('contact_id', 'organization_id') with no added semantics. The description does not elaborate on these parameters either. Since schema coverage is 100% but trivial, the description adds no extra value, so a baseline of 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?

The description clearly states the action ('Deletes one contact') and the resource ('tenant CRM'), distinguishing it from sibling operations like get, create, or update. The verb and object are explicit, leaving no ambiguity about what the tool does.

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 usage by naming the delete operation, but it does not explicitly compare with alternatives or state when to prefer this tool over others. It also doesn't mention when not to use it. However, the intent is clear enough that an agent can infer it's for removing contacts.

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