Triage change

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

Annotations already declare readOnly=false, destructive=false, and idempotent=true, so safety is largely covered. The description adds real value beyond them by disclosing that the status change is reversible ('unreviewed to put it back in the inbox') and what each state means semantically. It stops short of stating that only review_status is touched or what happens for an invalid change_id.

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?

A single front-loaded sentence with the action first and the three status options after. No filler, and every clause carries information an agent needs to pick a value.

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 only two required params, full schema coverage, an enum, and annotations covering the safety profile, the description covers what an agent needs to invoke it correctly. It could still mention that other change fields are untouched and where change_id comes from, but these are minor gaps given the schema already names list_changes and get_digest as id sources.

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% and both parameters, including the enum, are fully documented in the schema. The description's gloss on the three status values largely duplicates the schema's own enum descriptions, so it adds little semantic depth. Baseline 3 applies when the schema does the heavy lifting.

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 verb 'triage' is paired with a specific resource ('a change') and the exact field being mutated ('review_status'), so an agent knows precisely what the tool does. It is clearly distinct from the read-oriented siblings get_change and list_changes without needing to name them.

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?

The description gives concrete selection criteria for each status value: 'acknowledged when it is relevant, dismissed when it is noise, or unreviewed to put it back in the inbox'. That is clear usage context, though it never names alternatives (e.g., 'use get_change first to inspect details') or states any when-not conditions.

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