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

Annotations already state readOnlyHint=false and destructiveHint=false, so safety framing is partly covered. The description still adds real behavior beyond them: three-valued outcome, the 10-minute timeout collapsing to stop, the must_abort escalation, and the boundary that this tool does not itself deliver the post or CRM write. Those are substantive, so it clears the lower bar annotations set.

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-loads the obligation, then the return contract, then the wait path, then scope limits; nearly every sentence carries a distinct instruction. The phrase 'when the agent still executes after go' is slightly tangled and costs a little readability. No padding or repetition beyond that.

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?

With no output schema, the description correctly supplies the return vocabulary (go, stop, wait), the timeout rule, and the must_abort field that governs whether to act. It also bounds scope against slack.post, crm.write, and email. Sufficient to call and interpret correctly, though the shape of the response object itself is left implicit.

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 all five parameters are already documented, including action_type's example values and the optional risk and target fields. The description adds only the framing that preview is what executes after go, which largely restates the schema. Baseline 3 is correct when the schema does the work.

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 the resource (Action Gate) and states precisely what it returns: go, stop, or wait for a pre-action approval decision. It distinguishes itself from get_approval (the polling sibling) and clarifies it does not perform slack.post or crm.write. The opening label 'Action Gate Ask' is jargon, but the following sentence resolves it.

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?

Explicit trigger ('MUST be called before a consequential non-money action... including deploy'), explicit follow-up path ('If decision is wait, poll get_approval until go or stop'), explicit timeout behavior, and explicit exclusions with the correct alternatives ('To enforce those, call slack.post or crm.write. Email isn't supported yet'). It also names ask_human as an alias, removing ambiguity with a sibling of that name.

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