Update bill

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

With no annotations, the description carries the full burden. It usefully discloses the write mechanics (preview produces a token, confirm consumes it) and adds a real caveat that the connector does not send bills to clients. It omits permissions/auth requirements, whether state changes are validated or reversible, and what happens to unspecified fields, so the safety picture is incomplete.

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 tight sentences with the updated fields front-loaded, followed by the write workflow and a caveat. Every sentence adds information and nothing is padded.

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 mutation tool with no annotations, no output schema, and eight low-coverage parameters, the description covers the core fields, the confirm flow, and one important behavioral caveat. It still leaves gaps around the number parameter, the date formats, valid state transitions, and error/validation behavior.

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 13%, so the description must compensate. It names five of the eight parameters (subject, memo, issue/due dates, state) and clarifies that state is a workflow transition, but it never mentions the number parameter, gives no date format guidance, and only illustrates two of the five enum values.

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 (updates the bill header) and enumerates the affected fields (subject, memo, issue date, due date, state). It is clearly distinguishable from read-only siblings like clio_bill_get and clio_bills_list, so an agent can route correctly 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?

It flags the operation as a write and outlines a preview-then-confirm flow, which is genuine usage context. However, it states 'preview first, then confirm' as a rule, while the schema's own confirm description says to call with confirm=true directly when the request is complete — a mild conflict that could cause an agent to run an unnecessary preview round-trip.

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