update_change

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

With no annotations provided, the description must carry the behavioral disclosure burden. It does reveal that the operation is a mutation and that is has a non-obvious side effect: refreshing the Change Request's head revision. But it does not disclose whether this is reversible, whether it changes history or commits, or what permissions are needed.

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?

The description is one tightly written sentence with no filler. The main action comes first and the secondary effect is stated without wasted words.

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-parameter mutation tool, this is minimally adequate: it tells the agent what action to take and that there is an additional revision-refresh side effect. But with no output schema, no annotations, and a 0% parameter description coverage, the description leaves return behavior and the meaning of 'refresh head revision' largely unexplained.

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 0%, so the description should compensate for the lack of parameter documentation. It mentions 'rationale' by name but does not explain its format, that null may be used to clear it, or how change_id behaves as the target identifier. The agent gets little beyond the bare field names from 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?

The description names a specific verb ('Update') and resource ('a Change Request'), and specifies the exact scope: rationale plus refresh of head revision. This is enough to distinguish it from the many read-only and workflow sibling tools such as get_change, review_change, merge_change, and abandon_change.

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 intended use is implied clearly: call this tool when a Change Request's rationale must be updated. However, the description does not explicitly say when not to use it, nor does it contrast it with alternatives like create_change for a new change or abandon_change for discarding one.

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