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

Annotations only state destructiveHint=true, but the description goes far beyond that: it discloses the confirmation_required response with payload preview, that confirmWrite: true applies the previewed change only after explicit confirmation, that placeholder tokens are invalid, and that routeToken does not bypass preview or confirmation. This is exactly the kind of behavioral context an agent needs to avoid destructive mistakes.

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?

Six dense sentences with no filler. The purpose is front-loaded and every subsequent sentence explains a distinct, safety-relevant aspect of the transactional workflow. The length is proportionate to the complexity of a destructive two-phase commit tool.

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 19-parameter, destructive, two-phase transaction tool, the description covers the essential behavioral surface: token requirements, preview semantics, confirmation requirements, and the confirmation_required response path. It omits success-response shape and other error conditions, but since no output schema exists and the safety-critical flow is thoroughly documented, it is nearly complete.

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 coverage is only 42%, so the description should compensate for undocumented data parameters (note, total, details, totalNet, totalVAT, reference, etc.), but it does not. It does add meaningful narrative semantics to the critical transactional parameters (routeToken validity and confirmWrite protocol), which the schema also documents. The low coverage gap for data fields remains unfilled.

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 opens with a specific verb and resource — 'Updates a sales credit note' — and adds a distinguishing constraint: 'while preserving the existing BRC unpaid value.' This clearly differentiates it from creation, deletion, and batch siblings without needing to open any 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 description gives strong workflow context: it names the prerequisite (valid routeToken issued for the matching action workflow), explains the two-phase confirmWrite protocol, and states that preflight is not confirmation. It does not explicitly name alternatives (e.g., use brc_create_sales_credit_note to create), but the update-versus-create distinction is clear enough from context.

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