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

Annotations only mark this as non-read-only and non-destructive, so the description carries the full burden. It discloses that this is a real financial document, is irreversible, takes a sequential number, posts to the general ledger, and must be corrected via a credit note. This is exactly the kind of behavioral consequence an agent needs beyond 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?

Three short paragraphs with no filler. The irreversible financial warning and usage instructions are front-loaded, and the parameter mapping guidance is tightly written.

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 financial mutation tool with no output schema, the description covers the core action, parameter decision rules, user confirmation step, and post-issuance correction path. An agent has enough safety-critical context to invoke the tool 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?

With schema description coverage at only 14%, the description compensates for the most decision-critical parameters: taxTreatment maps to VAT registration status and type maps to simplified vs standard with a buyer VAT number requirement. Other parameters are largely self-explanatory or already described in the schema, so the remaining gaps are minor.

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-resource pair ('Issue a tax or ordinary invoice') and clearly distinguishes itself from sibling get/list/vat tools by emphasizing real accounting effects: next sequential number, VAT computation, ZATCA QR code, and general ledger posting. The scope is unambiguous.

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?

Provides explicit selection rules for taxTreatment and type, and instructs the agent to confirm amounts with the user before calling. It does not explicitly name alternative sibling tools or exclusion conditions, but the 'cannot be edited afterwards' warning strongly implies when to avoid direct use.

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