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

Annotations already indicate destructive behavior, and the description adds specific context about what gets destroyed (skills, tools, grading suites, sessions, connectors). This goes beyond the generic destructive hint and gives the agent concrete information about the impact of the operation.

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, concise sentence that front-loads the action and resource, with a parenthetical list of affected data types. Every word earns its place and there is no redundancy.

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 tool with one required parameter, the description, schema, and annotations together provide complete information: what the tool does, what it destroys, and the required parameter. The lack of an output schema is acceptable for a delete operation.

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 input schema fully documents the single parameter (agent_id) with a clear description. The tool description does not add any additional semantic detail beyond what the schema provides, so the baseline score 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 clearly states the action (permanently delete) and the resource (agent), along with the scope of data affected (skills, tools, grading suites, sessions, connectors). This distinguishes it from sibling tools like get_agent, update_agent, or create_agent.

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 this tool is for permanent deletion but provides no explicit guidance on when to use it versus alternatives such as export_agent or update_agent. It does not mention prerequisites, fallback options, or cautionary notes, so it lacks clear exclusions or alternatives.

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