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

Annotations only cover the safety profile (readOnlyHint, destructiveHint=false), and the description goes well beyond them: it discloses the total-vs-page pitfall explicitly ('total is counted across every pending row, actions is the page you asked for'), the one-connection scoping invariant, and the deliberate inability to mutate. This is exactly the behavioral context annotations cannot carry.

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 core purpose in the first sentence and every subsequent sentence carries distinct content (provenance, pagination trap, scoping, no-mutation). The all-caps emphasis and the aside about a past shipped mistake are slightly noisy and cost it a point, but there is no dead weight.

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?

No output schema exists, yet the description enumerates what each row contains (the record changed, the field changes, the reviewer reasoning, the originating run or plan), plus connection scoping and paging semantics. Nothing an agent needs to call this list correctly and interpret the result 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?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning by hammering the semantics of limit/offset versus the returned total ('THE COUNT IS THE CONNECTION'S WHOLE PENDING TOTAL AND NOT THE PAGE'), which prevents a misread of the limit parameter's scope. It also reinforces the connection_id dependency suggested in the schema.

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 and resource ('what is waiting for a person to decide' — listing queued changes), and immediately distinguishes itself from queue_action and the run-producing siblings by declaring it is the only place undecided proposed rows exist. An agent can separate this from list_queue_history, list_runs and list_plans 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?

Gives a clear governing condition for use ('THIS IS HOW YOU SEE WHAT YOU PROPOSED') and an explicit exclusion ('YOU CANNOT DECIDE THESE' — approving/rejecting/rolling back belong to a person). It also names queue_action as the producer of these rows. It stops short of routing the agent to a specific alternative for decided/historical rows (e.g. list_queue_history), so it is clear context without full alternative mapping.

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