retire_process_definition

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

Beyond destructiveHint=true and readOnlyHint=false, it discloses the exact blast radius, the treatment of running instances and their version pinning, and reversibility by republishing. These details substantially clarify a destructive operation and are consistent with the annotations.

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 are front-loaded with the action and then cover in-flight behavior and recovery. There is no filler, and each sentence adds operationally useful information.

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 destructive lifecycle tool, the description, schema, and annotations provide enough to invoke it and understand its main consequences. It is not fully complete for tool selection because the relationship to disable_process/enable_process is unexplained and the restoration step only generically says to publish again.

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?

The sole required key parameter is already fully documented by the schema, including its definition-key role, pattern, and example, so the baseline is 3. Saying that all published versions "da key" are affected adds operational scope but no further parameter selection or format semantics.

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 gives a specific verb and resource, then precisely states that every published version of the key becomes unavailable for agents to open. It does not explicitly distinguish retirement from the sibling disable_process, so it is clear but not fully differentiating.

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 supplies practical context: retire a process to block new openings while allowing in-flight instances to finish, and republish to restore availability. However, it gives no explicit when-not guidance or comparison with disable_process/enable_process, and "publique de novo" does not name publish_process_definition.

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