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

Annotations already declare destructiveHint=true. The description adds useful blast-radius context by saying only draft metadata is edited, which tells the agent this does not publish or alter live content. It still omits whether the change is reversible and what permissions/validation the endpoint enforces, so it is a modest value-add rather than a rich disclosure.

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, front-loaded with the action and scope, then the endpoint. Every sentence earns its place with zero filler.

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?

Given 4 params, no output schema, and only a destructiveHint annotation, the description covers what can be changed and the endpoint. It leaves notable gaps: no indication of valid status values (the schema has no enum for a clearly enumerable field) and no note on the response or side effects of the destructive update.

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 the required spaceId/changeRequestId are documented in the schema, so the schema carries the burden. The description names the two mutable fields (subject, status) and the REST path, but adds no format, allowed status values, or validation detail beyond 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 (Update), resource (change request), and the exact editable fields (subject or status), which cleanly separates it from the sibling create/list/get operations. The PATCH endpoint reference reinforces the mutation semantics.

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?

'Edits draft metadata only' gives an implied scope for when this tool is appropriate, but there is no explicit when-to-use vs. alternatives guidance (e.g., use update vs. create_change_request, or that publishing is out of scope). The agent must infer the routing from the name.

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