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

No annotations exist, so the description carries the load, and it discloses several behaviors: the record starts as a draft (not sent), tax defaults to shop rate unless overridden, and the total can be negative (a credit). It doesn't mention permissions/auth or cancellation, but core mutation behavior is well covered.

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?

Front-loaded with the core action and definition, then adds the essential behavioral notes in dense but purposeful clauses. No wasted sentences.

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, an output schema present, and 5 params, the description covers the key behavioral facts (draft status, tax defaulting, credit possibility) plus the follow-up tool. Permissions and edit/cancel mechanics are not covered but are secondary.

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 20%, so the description must compensate and does: it explains discount lines ('take work out'), credit totals, and tax semantics ('shop default rate unless tax_rate_id is given; null for no tax'). It says less about title/description/job_id, which are largely self-evident.

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 (write) and resource (change order on a job), and defines what a change order is ('a priced change to its scope'). It also distinguishes itself from the sibling changes_send by noting it 'starts as a draft' and is sent later via changes.send.

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?

Clear workflow context: use this to create a draft, then call changes.send to send it to the customer. It doesn't explicitly enumerate when NOT to use it, but the alternative action and staging behavior make the intended usage unambiguous.

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