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

Annotations already declare destructiveHint=true, and the description adds meaningful behavioral detail beyond that: it removes BotInstances as well as the Agent, and requires an environment variable gate. This gives an agent a clear picture of the side effects and invocation prerequisites. It does not contradict the annotations, and it enriches the safety profile with specific consequences.

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 two sentences with no filler. The core action and endpoint lead, followed by the destructive consequence and the gating condition. Every sentence earns its place and the structure is easily scannable for an agent.

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 single-parameter delete tool, the description is complete: it names the action, endpoint, affected resources, and enabling condition. The schema covers the parameter format, and annotations cover safety flags. No output schema exists, but explaining return values is not essential for a delete operation with this level of transparency.

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 parameter 'agentIdOrAddress' is already well-documented in the schema as a Mongo _id or EOA-style address. The description adds no additional parameter-level meaning, but with full schema coverage the baseline score of 3 is appropriate. No extra clarification is necessary here.

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?

Description clearly states the tool's action: 'Delete an Agent' with the exact endpoint. It also specifies the scope of destruction ('removes the saved Agent and its BotInstances'), which distinguishes it from other agent-related tools like update, activate, or clone. This is a specific verb+resource definition with no ambiguity.

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 provides important usage context by warning that the tool is destructive and gated behind ETHORA_MCP_ENABLE_DANGEROUS_TOOLS. However, it does not explicitly guide an agent on when to choose this over alternatives, such as deactivating an agent rather than deleting it. The safe-use precondition is stated, but exclusionary or alternative guidance is absent.

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