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

The annotations already declare destructiveHint=false and openWorldHint=true, so 'Never publishes' adds real value by confirming the outcome stays a draft. However, the description does not address the un-idempotent nature of the call (idempotentHint=false), the expected_version concurrency requirement, or what happens to prior drafts.

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 compact, front-loaded sentences with no filler. The title duplicates the first sentence, but the body itself is efficient and the 'Never publishes' caveat lands at the end where it matters.

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?

A mutating, non-idempotent, open-world action with eight parameters, no output schema, and 25% schema coverage needs more than two sentences. Required fields like job_id, key, expected_version and environment are left entirely unexplained, so an agent cannot call this correctly from the description alone.

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 only 25%, so the description should compensate but does not. Of eight parameters, only 'origin' gets a hint ('give its https origin'); key, job_id, company, environment, expected_version, effect_id and idempotency_key are undocumented in both the description and 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 states a specific verb and resource – 'Save one piece of approved work as a draft company action' – and explains the two source forms (a task's instructions or an API call's method/path/body). 'Never publishes' implicitly separates it from summer_actions_company_publish, but it never names a sibling or says how it relates to summer_actions_company_save.

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?

'Replace case details with inputs, test and publish it like any other action' implies a workflow for how to proceed, but there is no explicit when-to-use, when-not-to-use, or named alternative. The agent must infer when to use this versus company_save or actions_prepare from the description alone.

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