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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the safety profile is covered; the description adds substantial value by clarifying what survives (transaction and ledger history) and what is explicitly NOT done (no cash out, refund, or fund transfer). It does not explain behavior on a repeat call against an already-revoked key, even though idempotentHint=false flags that as a meaningful case.

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 sentences, front-loaded with the irreversible effect, then the preserved state, then the usage boundary. Every sentence carries distinct decision-relevant information with no repetition of the title or annotations.

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 zero-parameter, no-output-schema mutation tool with full annotation coverage, the description says everything an agent needs: what is disabled, what remains, what is not performed, and when to choose it. Nothing material is missing.

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?

The tool takes zero parameters, so there is no parameter semantics to convey and the baseline is 4. The description correctly scopes the action to the authenticated machine rather than implying any selector argument exists.

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?

Names a specific verb and resource: permanently disable the authenticated sandbox machine's current API key, and states the downstream effect (wallet and purchase requests with that key are blocked). This clearly separates it from siblings like register_machine, set_wallet_limits, or revoke_card_authorization.

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 both a when ('decommissioning or securing the machine') and an explicit when-not ('not when merely changing spending limits'), which also implicitly routes the agent to set_wallet_limits for the adjacent case. No inference required.

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