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

Annotations already declare write-like, non-idempotent, open-world behavior, and the description adds the crucial consequence beyond them: 'The run goes on at once', telling the agent the reply immediately resumes the run and cannot be staged or undone. It also clarifies the allow=true / allow=false polarity, which is a decision-semantics detail rather than a restatement of the hint flags.

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, front-loaded with the core action and its preconditions, with no filler. Each sentence adds a distinct piece of information: what it does, the two modes, the escalation rule, and the immediate consequence.

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 described, and the tool is structurally simple with only one required parameter. The description covers mode, precondition, escalation, and consequence; the only gap is what happens on a run that is not actually waiting (error behavior) or whether 'text' can also be a free-form answer to a permission prompt.

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 100%, so all three parameters, including the mode split between 'text' and 'allow', are already documented in the schema. The description reinforces which parameter belongs to which mode ('with text' vs 'allow / decline'), which is a small addition of meaning, but it introduces no format, constraint, or edge-case detail beyond the structured fields.

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 uses a specific verb and resource: 'Reply to a run that waits for you', and immediately enumerates the two operating modes (answer a question with text, or allow/decline a permission step). That is concrete enough to act on without opening the schema, but it does not name or differentiate against siblings like 'run', 'run_status', or 'act', so an agent must infer the boundary itself.

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?

It states the precondition clearly ('a run that waits for you', reinforced by the schema's 'status paused, waiting_for') and gives a genuine exclusion rule: if the question is something only the user knows, ask the user first. What is missing is any routing guidance versus neighbouring tools such as 'run_status' (to check whether a run is actually waiting) or 'act'.

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