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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so 'Nothing stored or sent' largely restates them. The description still adds real context beyond the structured data: the returned artifacts (JSON, calculated totals, editable builderUrl) and the warning that 'Example amounts need review'.

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 compact sentences, front-loaded with the action, then the outputs, then the two caveats. No filler; each clause carries distinct information.

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 6 parameters, nested from/billTo objects, and no output schema, the description usefully describes the return shape (invoice JSON, totals, builderUrl) and the non-persistence guarantee. The main omission is routing guidance among the three sibling tools, but for a single read-only preparation step the coverage is solid.

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 83%, above the 80% threshold, so the schema already documents the from/billTo/number/date fields. The description only groups them as 'sender, customer and dates' without adding format or constraint detail beyond what the schema provides, which is the baseline case.

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 ('Select a template by ID and add sender, customer and dates') and describes the return payload (invoice JSON, totals, builderUrl), which implicitly separates it from render_invoice_pdf and list_invoice_templates. It never names those siblings explicitly, so the differentiation is inferential 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 caveat 'Nothing stored or sent' hints this is a safe preview step, and the templateId enum shows the required selection. However, there is no explicit guidance on when to use this versus draft_invoice or render_invoice_pdf, nor any stated prerequisite such as listing templates first.

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