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

Annotations say destructiveHint=false and readOnlyHint=false, but the description adds real behavioral context beyond them: the operation is refused when agents are still on the plan, and the refusal names those agents. That is genuinely useful pre-call information an agent cannot get from 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?

Two short sentences, front-loaded with the prerequisite, then the action, then the failure condition. No wasted text, though the parenthetical prerequisite opening slightly buries the actual verb.

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 full schema coverage and no output schema, the definition covers prerequisites, the action, and the blocking condition. It does not say what happens after archiving (e.g., whether the plan can be restored), but nothing essential to invoking it is missing.

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 coverage is 100%, so both parameters are already documented, and the description only adds the provenance constraint that workspace_key comes from create_workspace. Baseline 3 is appropriate since the schema carries the parameter detail.

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?

"Retire a plan nobody uses any more" states a specific verb (retire/archive) and resource (plan). It distinguishes the operation from siblings like update_plan or list_plans, though it never explicitly names an alternative tool for the delete/update case.

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?

Usage is implied: use this to retire an unused plan, and it will be refused while agents remain assigned. There is no explicit guidance on when to prefer update_plan instead, nor on prerequisite ordering beyond the workspace_key parenthetical.

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