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

The destructive hint annotation already flags mutation, but the description adds valuable behavioral detail: deletion is conditional on absence of references, and refused deletions list the offending documents. This goes beyond the annotation and helps an agent predict failure modes.

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 sentences carry the full meaning: the first states the operation and precondition, the second states the failure behavior. There is no redundant phrasing or filler.

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 single-parameter destructive tool with annotations and full schema coverage, the description is complete: it defines the valid target, the constraint, and the refusal response. No output schema is needed to make correct use unambiguous.

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 client parameter already specifies 'Client name or id, exactly as client_list shows it'. The description adds no parameter-specific information, so the baseline of 3 applies.

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 opens with a specific verb and resource: 'Delete one stored client', and adds a distinguishing scope condition ('that nothing refers to'). This separates it clearly from sibling tools like client_add and client_list, and the reference-refusal behavior adds further specificity.

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?

It states the condition under which the tool is appropriate: only clients with no references can be deleted, and it explicitly describes the refusal case when the client appears on any listed document. It does not name alternative sibling tools explicitly, but the condition is clear enough to guide selection.

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