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

Annotations only declare the safety profile (not read-only, not destructive, not idempotent); the description adds real behavioral context: the no-op case for already-held items and the not_found outcome ('it already went out, or is not pending'). That is useful state/error disclosure beyond structured fields, though it says nothing about auth or limits.

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?

Two front-loaded sentences that establish what it does, when to use it, and the no-op case, with the error note appended compactly. The colon-heavy 'not_found:' fragment is slightly cryptic but earns its space.

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 two-param mutation with no output schema, the description covers purpose, ordering, no-op behavior and the primary failure mode, which is most of what an agent needs. It stops short of describing the resulting state changes or the confirm-guard interaction.

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 both action_id and confirm are fully documented in the schema, and the description adds no syntax or format detail beyond implying the id comes from the autopilot queue. Baseline 3 is correct when the schema carries the parameter 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?

States a specific verb (hold) plus the concrete resource instances it acts on (an auto_send_after reply or a website batch on auto), and explicitly frames it as the counterpart to reviewing/rejecting. An agent can distinguish it from approve_autopilot_action and reject_autopilot_action without opening any schema.

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?

'Use before reviewing or rejecting one' gives clear ordering/context guidance and 'Items that already wait for an approval are left as they are' rules out a whole class of inputs. It does not name the sibling tools (approve_/reject_autopilot_action) explicitly, which keeps it just short of a 5.

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