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

Goes well beyond annotations by disclosing the exact state transition (Unfinished to Not sent), the downstream reporting consequence (counted in Accounting Act and tax reports), the per-call confirmation default and how to disable it, and the API key requirement. This is precisely the kind of operational context annotations can't carry.

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-loads what the tool does and the state change, then adds operational caveats. Slightly redundant: the per-call confirmation default and the 'Reaches other people: confirm with the user before each call' sentence partly repeat the same instruction.

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?

With a single fully-documented parameter, no output schema, and annotations already covering the safety profile, the description supplies everything else an agent needs: prerequisites, state transition, reporting side effects, and human-confirmation requirements.

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?

Single parameter with 100% schema description coverage, so the schema already documents invoice_id (including its source tools). The description adds only an implicit state precondition (invoice must be Unfinished) rather than any parameter-specific meaning. 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 (Approve) and resource (sales invoice) with the precise precondition ('an Unfinished sales invoice') and outcome ('so it can be sent'). The workflow role is clear enough to distinguish it from sibling send_sales_invoice, which requires an already-approved invoice.

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 description establishes the workflow condition ('Only approved invoices can be sent') which effectively tells the agent when to reach for this tool before sending. However it never names the alternative sibling (send_sales_invoice) explicitly, so the routing is implied rather than stated.

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