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

This is the standout dimension. The description discloses a critical side effect beyond what annotations declare: 'the SDK swallows the failure, so nobody gets an error, the data simply stops.' This tells the agent that revocation is silent and consequence-bearing, which is exactly the behavioral context needed for both invocation and communication with the user. It complements the destructiveHint=true annotation rather than merely repeating it.

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?

Three short sentences, each earning its place: the core action, the behavioral consequence, and the caution. The most important information is front-loaded, and there is zero filler or repetition of the title.

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?

Given the destructiveHint annotation and presence of an output schema, the description covers what matters most: the immediate effect, the silent failure mode, and a warning to verify the target key. The only minor gap is that it never explicitly states whether revocation is reversible or what to do if the wrong key is revoked, though 'Be sure which key it is' strongly implies irreversibility.

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 the schema already documents both parameters in detail, including how to identify a key ('by its `mp_live_…` prefix or its id') and an mcp ('matched case-insensitively'). The description adds no parameter-level information, which is acceptable given the baseline of 3 when the schema carries the load.

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 opens with a specific verb-resource pair ('Stop a key working, immediately'), which unambiguously states what the tool does. It is clearly distinguished from siblings like list_keys and list_mcps, which read or list rather than revoke. The title reinforces the same action without redundancy.

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 establishes a usage context: this is the tool to use when you want to immediately disable an ingest key. It implies a precondition ('Be sure which key it is') suggesting prior verification before invocation. However, it never explicitly names an alternative or states when not to use this tool; the guidance to consult list_keys/list_mcps lives in the schema parameter descriptions, not the description itself.

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