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

With destructiveHint=true already declared, the description adds what the annotations cannot: which actions preserve artifacts ('stop — keeps everything made', 'cancel_build — free; what it wrote stays'), that 'continue' clears the current checkpoint, and that three actions re-enable spending and need a spend-scope key. That is concrete consequence and authorization context an agent needs before firing a destructive call.

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?

Front-loaded with the purpose, then a single dense run of mid-dot-separated action glosses; every clause carries real information and there is no filler. The extreme density makes it harder to scan for a single action than a short bulleted list would, which caps it at 4.

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 three-parameter, destructive control tool with no output schema, the description covers action semantics, cost, artifact retention and spend authorization. Remaining gaps are minor: project_id scope is never explained and no return/confirmation behavior is hinted at.

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 only 33% (only cap_credits is described), and the description compensates strongly by defining the semantics of all seven action values, including which are irreversible or spend-enabling. project_id is left completely undocumented in both schema and description, which keeps this below 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+resource ('Operate a live run') and then enumerates all seven actions with a short gloss for each, so an agent knows exactly which operation each enum value performs. It also implicitly routes away from siblings by naming the greenlight question and the review step that gate 'decline' and 'continue'.

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 explicit preconditions for the risky actions ('continue' only after human approval of what review showed; 'raise_cap' only with a human-approved cap; 'decline' dismisses the greenlight question) and states that resume/continue/raise_cap re-enable spending and require a spend-scope key. It stops short of saying when to prefer pause vs stop vs cancel_build beyond their one-word glosses.

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