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

Annotations only supply readOnlyHint=false, so the description carries most of the burden and does it well: it discloses the downstream filing gate and the re-eligibility side effect of turning it off, plus the required capability (company.settings_own). It stops short of saying whether the setting is company-wide for all team members or confirming reversibility after filings are already queued.

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 front-loaded sentences carry the toggle semantics, and the trailing capability note is compact and useful. The phrasing 'no case of yours is filed until you approve its current draft' is slightly compressed but earns its words.

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 state-changing setting with no output schema, the description covers purpose, both state semantics, and the linked approval tool. The remaining gap is verification/rollback guidance if the toggle lands in an unintended state.

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?

With 50% schema coverage, the undocumented parameter is 'on', and the description does compensate by spelling out what On and Off mean operationally. The 'company' parameter is documented in the schema, but the description adds nothing about multi-company scoping beyond saying 'your company's'.

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 names a specific verb+resource pair: it turns the company's filing-approval policy on or off. It also defines both states and points at the directly coupled sibling approve_filing, so an agent can distinguish this settings toggle from the rest of the sibling list without opening the schema.

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 context is explicit — enabling means nothing is filed until approve_filing is called on the current draft; disabling sends approval-only cases back through eligibility immediately. That tells the agent the consequences of each branch, but it never states prerequisites (e.g. required role) or when the agent should avoid flipping the policy.

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