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

Annotations already cover read-only and idempotent behavior. The description adds context beyond those: it emphasizes that this is validation only, surfaces that it is cheaper than read_invoice, and tells the agent what classes of results to expect. No contradiction with annotations.

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 focused sentences with no filler. The first sentence front-loads the tool's purpose and output scope, and the second sentence provides a crisp decision rule against a sibling. 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?

With a full output schema, complete parameter documentation, and safety annotations, the description covers the remaining selection context: what this tool returns, its validation-only scope, and when it is preferable to read_invoice. Nothing essential is missing for an agent to choose and call it correctly.

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 the schema fully documents lang, path, and file_base64. The description does not add parameter-level detail, but it also doesn't need to; the baseline 3 applies because the schema carries the burden.

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?

The description states a specific action ('Validation only') and resource ('invoice'), then enumerates the concrete outputs: applied rule sets, errors/warnings with fix hints, and invoice header. It clearly distinguishes itself from read_invoice by framing itself as a cheaper validation-first alternative.

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 explicitly names the sibling tool read_invoice and gives the condition for choosing validate_invoice: when you 'only need a verdict.' This is direct when-to-use guidance and makes the trade-off clear.

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