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

Annotations already declare destructiveHint=true, so the bar is lower, but the description goes further by naming the consequences: the action cannot be undone and every client using the key stops authenticating. That is exactly the impact context an agent needs before calling a destructive tool.

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?

Four short sentences, front-loaded with the action and its equivalence, followed by consequences and required inputs. No filler or repetition.

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?

An output schema exists, so return values need not be explained, though the description briefly notes the deleted key ID is returned. For a two-parameter destructive tool, everything needed to call it correctly is present.

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 has to carry the burden, and it does name both required inputs and their source (org ID, key ID from GetApiKeys). It does not document formats or constraints on the two string IDs, which keeps it short of a 5.

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?

States a specific verb and resource: 'Delete an API key from an organization', and anchors it to a known equivalent (`rover api-key delete`). It is trivially distinguishable from siblings like CreateApiKey, RenameApiKey and GetApiKeys.

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?

Tells the caller exactly what to supply ('Provide the organization ID and the key ID') and where the key ID comes from ('which GetApiKeys returns'), routing the agent to the sibling that produces the input. It does not spell out when-not to use it, but for a delete tool the context is clear enough.

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