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

Annotations already mark destructiveHint=true and readOnlyHint=false, indicating a write operation. The description adds useful behavioral context: 'soft-delete' implies recoverability Secretly may not be true, and 'running executions stop' discloses the immediate side effect. These are beyond the annotations. However, it does not clarify whether the deletion is reversible, what happens to associated data, or if any cascading effects occur. A 3 is appropriate because the soft-delete distinction adds value but not enough detail about the full behavioral impact.

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 sentence, highly concise and front-loaded with the primary action. The behavioral effect is included immediately after the action. There is no wasted wording; every word adds clarity. It is appropriately sized for a simple tool with one parameter.

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 is a delete operation with one parameter and no output schema, the description is minimal. It does not mention return behavior (likely success/failure), error conditions (e.g., invalid id), or irreversible consequences. It also does not specify whether the operation is idempotent or what happens to ongoing executions in detail. The annotations cover destructiveness, but the description is too sparse to be considered fully complete for an agent to use without additional assumptions.

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 0%, so the description must compensate for the lack of parameter documentation. The only parameter is 'id' (number), but the description does not explain what 'id' refers to (likely the campaign ID) or whether it is required (though schema says required). The description does not add any detail about the parameter beyond what is in the schema, leaving an agent to guess the id's purpose. Since coverage is 0%, the description fails to provide the minimal clarification that 'id' is the nurture campaign identifier.

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 ('soft-delete') and the resource ('nurture campaign'), and it is distinguished from the many other delete tools by specifying the exact resource type. It also notes a side effect ('running executions stop'). However, the term 'soft-delete' is specific and adds clarity, though it does not explicitly distinguish from the other delete tools beyond the resource type, which is sufficient given the naming convention.

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 when to use this tool (when you need to soft-delete a nurture campaign) but provides no guidance on when not to use it or alternatives. For instance, it does not mention whether there is a hard delete option or if there are prerequisites (e.g., campaign must be paused). The 'soft-delete' implies reversibility but does not explain how to undo it, which could mislead an agent into thinking deletion is permanent.

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