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

Annotations already declare destructiveHint=true, idempotentHint=false, readOnlyHint=false and openWorldHint=true, so the safety profile is known. The description adds context the annotations cannot: that this operates on a review queue, that items originate from list_actions' readyToApply set, and that explicit user consent is required before calling — a genuine behavioral constraint that guards against premature application.

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, each doing distinct work: what it does, the consent precondition, and where the ids come from. The precondition and provenance are front-loaded with no filler or restatement of the tool name.

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 one-parameter tool with rich annotations and no output schema, the description covers purpose, precondition, and id source. The only minor gap is not noting upstream errors when a change is no longer in Ready to apply, but an agent has everything needed to call it correctly.

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% and the single parameter is already documented, so baseline would be 3. The description earns the extra point by adding provenance semantics — the ids must come from list_actions (readyToApply), not arbitrary or invented identifiers — which meaningfully constrains how to populate change_ids.

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 ('makes changes') and a specific resource/state ('changes waiting in Ready to apply', clarified as saved-for-review or away-suggestions). This clearly distinguishes it from dismiss_change and undo_change siblings, though the phrasing is slightly oblique compared with the title 'Approve waiting changes'.

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?

Explicitly gates usage: 'Only for changes the user has said yes to,' which is a real precondition rather than generic advice. It also names the upstream source of ids ('Ids come from list_actions (readyToApply)'), leaving only the contrast with dismiss_change implicit rather than stated.

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