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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds useful context by naming the specific data components returned, but it does not disclose authorization requirements, not-found behavior, or pagination characteristics.

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 a single front-loaded sentence with no wasted words. It is appropriately sized, though it is nearly identical to the title and does not use the space to add parameter or usage guidance.

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?

There is no output schema, so the description helpfully identifies the major returned components. However, for a tool with three required parameters and 0% schema description coverage, it is incomplete because it leaves all parameter semantics undocumented.

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%, and the description provides no meaning for the three required parameters. It does not explain that 'company' is a UUID, 'environment' selects staging vs production, or that 'key' must follow the company.* pattern.

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 clear verb and resource: 'Read one company action.' It also enumerates what is returned (draft, published revision, revision history, stage, stage history), which distinguishes it from mutation siblings such as summer_actions_company_save, publish, and retire.

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?

The description implies a read use case but gives no explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites, when to prefer save/publish/test, or whether this is the canonical read endpoint for company actions.

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