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

With no annotations, the description carries the full behavioral burden and does so richly: returns an approval_url, requires the target owner's click, old key dies immediately on approval, new plaintext is deliberately withheld and delivered out-of-band, and the target agent is expected to go offline until handoff.

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?

Five sentences, each carrying distinct information, with the core action and its cross-agent scope front-loaded before the approval mechanics and the warning about the withheld plaintext.

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?

No output schema exists, yet the description explains the return value (approval_url), the async approval flow, and the downstream consequence for the target agent. An agent has everything needed to decide and invoke correctly.

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%, so both parameters are already documented; the description adds no format, length, or selection guidance for target_agent_id or reason beyond the schema. Baseline 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?

States a specific verb (rotate), the exact resource (another agent's active API key), and the concrete effect (mint new + revoke old). The 'ANOTHER agent's' qualifier cleanly separates it from the sibling rotate_api_key, which operates on the caller's own key.

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?

Gives a clear trigger ('Use when you've spotted leakage') and points to request_revoke_agent_key as the same-shaped alternative. It never explicitly names the when-not case (self-key rotation via rotate_api_key), though 'ANOTHER agent's' strongly implies it.

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