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

With destructiveHint=true already declared, the description earns credit for explaining WHY it is destructive: 'only the fields you pass change, but line_items (if passed) replace every existing line' plus 'Does not send anything.' That patch-vs-replace distinction and the no-side-effect-on-send note are exactly the behavioral context an agent can't get from the annotation flag alone.

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?

A single compact sentence delivers the patch semantics, the destructive line_items caveat, the no-send guarantee, and the endpoint mapping. Every clause earns its place and the most important caveat is front-loaded.

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 17-parameter mutation with no output schema, the description covers the two things an agent most needs: partial-update behavior and the destructive line_items replacement. It omits any mention of required permissions or how a successfully updated invoice is surfaced, which is a minor gap given no output schema exists.

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 100%, so baseline is 3, but the description adds non-obvious semantics the schema only repeats: that line_items is a wholesale replacement of all existing lines rather than a merge. That materially changes how an agent should populate the parameter.

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 ('Edit an invoice') and pins the underlying operation to PUT /api/v1/invoices/{id}, which cleanly separates it from create_invoice or email_invoice. It stops short of naming any sibling explicitly, so the differentiation is implied by the verb rather than stated.

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 phrase 'Does not send anything' hints that sending is handled elsewhere (email_invoice / mark_invoice_sent), but the alternative is never named and no when-to-use condition is spelled out. Usage is only implied.

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