commerce_contract_to_pay

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

Annotations already carry the safety profile (readOnly=false, idempotent=false, destructive=true, openWorld=true), so the description does not need to restate it. It adds value by disclosing the dispatcher routing and auth scope (JWT, tenant, company). It does not add context about financial side effects or what the 'contract_to_pay' action mutates, but the annotations lower the burden.

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?

The description is short, front-loaded with the action, and contains no filler. The Args block is clean and readable. It could earn a 5 if the action's purpose were more fully described, but every included sentence serves a purpose.

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 potentially destructive action with an opaque name and many sibling tools, the description is incomplete: it omits what the action does, what a successful invocation produces, and which scenarios call for it. The presence of an output schema and annotations mitigates return-value and safety gaps, but not the core selection/meaning gap.

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 0%, so the description carries the burden for parameters. It clearly distinguishes message as a free-text objective and inputs as an optional JSON string of structured inputs, adding meaning beyond the empty schema property titles. It stops short of describing the expected input keys or message format, but it is sufficient for a generic dispatcher-style action.

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?

Description states a concrete verb ('Run') and names the exact action ('contract_to_pay') plus its domain ('commerce'), so it is not a pure tautology. However, it does not explain what contract_to_pay actually accomplishes, and it does not differentiate it from closely named siblings like commerce_order_to_invoice or procurement_contract_to_pay. An agent would have to infer the business meaning from the tool name.

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?

There is no guidance on when to choose this tool over alternatives, nor any exclusion conditions. The only contextual note is that it routes through the domain-agent dispatcher under JWT/tenant/company scope, which explains invocation context rather than selection criteria. With several commerce/procurement contract-to-pay siblings present, this is a notable gap.

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