Approve invoice

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description discloses the resulting state (SAVED) and the accounting consequence of posting to the books, which is exactly the context a mutation tool needs. It does not cover failure behavior for non-draft invoices or whether the approval can be reversed.

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 sentences, no filler, with the effective state change front-loaded and the negative scope (no email) placed last. Every clause earns its place.

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 single-parameter mutation with annotations and no output schema, this covers what the tool does and what state it leaves behind. The only real gap is preconditions and error behavior for invoices that are not in draft.

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?

Only one parameter (invoiceId) exists and schema description coverage is 100%, so the schema already carries the semantics. The description adds nothing about the identifier's origin or constraints, so the baseline 3 applies.

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 ("Approve a draft invoice") plus the concrete effect ("posts it to the books (status SAVED)"). The closing clause "Does not email it" separates it from wave_send_invoice and wave_mark_invoice_sent without needing to open either 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?

The word "draft" implicitly scopes when this applies, and "Does not email it" steers the agent away from conflating this with sending. It stops short of naming siblings explicitly (e.g. use wave_send_invoice to deliver it) or stating what happens on a non-draft invoice.

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