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

The annotations already tell us this is destructive (destructiveHint: true) and not read-only, so the basic safety profile is covered. The description adds a specific behavioral consequence: the D number on a schedule is never reissued, which informs the user of a lasting side effect beyond the deletion itself. It also implies refusal behavior for non-planned states, but doesn't specify error codes or whether the operation is atomic. That's a modest but valuable addition beyond the annotations.

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 a single, compact paragraph: two clear sentences plus a short standalone sentence about the D number. It front-loads the core action and the critical restriction, and every sentence contributes to the user's decision-making. There is no fluff.

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?

Given the tool has only 2 parameters, both fully documented in the schema, no output schema (so no return values to explain), and annotations already carry the destructive hint, the description covers the essential usage context: what is deleteable, what is refused, what the alternative is, and a key invariant. Nothing critical is missing for an agent to decide to call it and pass the correct parameters.

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 already fully documents both parameters with examples and clarifiers (e.g., schedule: 'The schedule id... or its title'), so description doesn't add much. The description does add the nuance that the deliverable must be 'planned' and that the D number is never reissued, which indirectly clarifies the semantic scope of the deliverable parameter. However, since schema coverage is 100%, the baseline of 3 is appropriate, and the description provides marginal extra context.

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 (delete) and the resource (a planned deliverable), and immediately distinguishes it from deleting a schedule by using the specific resource name. It also clarifies the scope: only deliverable still planned with no history are deleteable, which carries precise semantic intent.

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 explicitly states when NOT to use it: one started, delivered, or accepted is refused, and names the alternative ('add a corrected deliverable instead'). This is an explicit when-not and alternative guidance, which is exactly what the dimension asks for.

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