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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is partly covered. The description goes beyond that by stating that the server chooses the agent and that no version is ever activated, which reassures an agent that this request has no live-production effect. It does not describe what the call returns or how the created improvement is identified, which keeps it at a 4.

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 short, front-loaded with the purpose, and each sentence adds distinct information (trigger, exclusion, next step, limits, example). The telegraphic, label-colon style ('Limits:', 'Next step:') is efficient but slightly reads like shorthand rather than prose.

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 with no output schema, the description supplies the trigger, the exclusion precondition (open work or cool-down), the fact that no version is activated, and a follow-up tool for checking outcome. What is missing is any statement of what a successful call yields (e.g., an improvement identifier) beyond directing the agent to improvement_status.

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 must carry the burden, and it only partially does so via the example {"workflowId":"invoice-flow","reason":"Missing lines"}. That example usefully shows workflowId identifies a target workflow and reason is a short free-text problem statement, but neither parameter is explained in prose, and the 500-character reason limit is left to 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 opens with a concrete verb and resource: 'Ask the server to open one workflow improvement,' which tells an agent exactly what the tool creates. It also names the sibling improvement_status as the follow-up, so it is distinguishable from the status-checking tool. The phrase 'open one workflow improvement' is somewhat domain jargon, which keeps it just shy of a 5.

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?

It gives an explicit positive trigger ('Use when a person reports a quality problem'), an explicit exclusion ('Do not use when work is open or in cool-down'), and a named next step ('call improvement_status'). This is the full when/when-not/alternative pattern an agent needs for routing.

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