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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds substantive scoping behavior beyond that: results are limited to the active company and include archived and merged classes, which materially affects what an agent receives.

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 what the tool returns. The trailing 'Set action to one of: list' is slightly awkward phrasing but carries real information. No filler.

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?

With five parameters, 20% schema coverage and no output schema, the description leaves too much unsaid: filtering semantics for name/names, the purpose of newName, and whether results are paginated or ordered. For a tool whose name implies mutation but whose only action is list, that ambiguity should be addressed head-on.

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 20% (just the `company` override), so the description must compensate for name, names, action and newName — and it does not. It never explains that name/names act as filters, and it leaves newName completely unexplained, which is especially confusing on a list-only operation.

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 (list) and resource (the active company's classes), then defines what a 'class' is in this domain (the locations, departments or properties a P&L can be read by). This separates it reasonably from manage_accounts/manage_categories, though it never explicitly contrasts with those siblings.

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 pins the only supported action ('Set action to one of: list'), which usefully resolves the mismatch between the 'manage_' name and a read-only tool. However, it gives no guidance on when to prefer this over sibling tools like manage_categories, and no conditions for using the name/names filters.

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