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

annotations already declare destructiveHint=true and readOnlyHint=false, so the agent knows mutability and risk without the description. The description adds only an intent guard, not the details that matter for a destructive call: irreversibility, whether attached event listeners or triggers are cascaded, or permission requirements. With annotations carrying the safety profile, a 3 is fair, but these gaps are meaningful for a delete.

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 short sentences, the action stated first and the guard second, with zero filler. Nothing is redundant or buried.

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 destructive, no-output-schema tool in a family of parallel delete_* siblings, the description omits cascade behavior, irreversibility, whether listeners bound to the command are removed, and how to confirm the right command_id. The single intent guard does not cover what an agent needs before running a delete.

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 coverage is exactly 50%: app_id points to list_apps, but command_id has no description anywhere. The description says nothing about either parameter, so the undocumented half is not compensated for and an agent gets no hint on how to obtain or validate command_id.

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?

"Deletes a command" names a specific verb and resource, so the purpose is unambiguous, but it is essentially the tool name and title restated with no added scope. It never distinguishes this from delete_event_listener or delete_message beyond the noun.

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?

"Only do this when the user asked for it" supplies a real use condition and implies a caution against proactive deletion, which is more than nothing. It names no alternative (e.g., set_enabled to disable, or get_command to confirm the target), so an agent still has to infer the safer path.

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