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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the description's job is to add consequence detail, which it does: in-flight approved work is halted and revisions/history are preserved. It still omits permission requirements and what happens on a version mismatch, which is notable for a destructive call.

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, each carrying distinct information: the operation, its immediate blast radius, and what is retained. The key scoping fact is front-loaded.

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 destructive, open-world mutation with no output schema, the description covers consequences and retention but leaves the agent without failure-mode guidance (stale expected_version), permissions, or recovery path. Adequate but with clear gaps.

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 only 50%, so the description should compensate, but it only alludes to expected_version ('with the expected version') without explaining the optimistic-concurrency conflict behavior. company, environment, key, and idempotency_key get no mention at all.

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 and resource: 'Remove a company action from the agent's catalogue'. This clearly separates it from the save/publish/get/test siblings in the summer_actions_company_* family, though it never names an alternative explicitly.

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?

'Approved work that uses it stops before it starts' implies when the operation matters, but there is no explicit when-to-use/when-not guidance and no mention of a safer alternative (e.g. pausing or re-publishing). The agent must infer that this is the terminal removal path.

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