Find sales invoice by reference

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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), and the description does not contradict them. Its added context — that matching is on a user-set reference such as a PO/project code — is useful, but it discloses nothing about result shape, multiple matches, or not-found behavior, which are the primary behavioral unknowns for a look-up tool.

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?

A single 18-word sentence that fronts the verb and resource before the clarifying example. There is no repetition of the title, no restating of annotations, and every word 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?

Adequate for a simple two-parameter read operation, but there is no output schema and no statement of what the call returns (single invoice vs list) or what happens when the reference is unknown or duplicated across invoices. That is the one material gap an agent would hit when deciding to call this tool or parsing its response.

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 50%: administration_id is fully documented (default behavior plus discovery hint), but reference has no schema description. The tool description compensates by defining reference as the value the user set and giving two concrete examples (PO, project code), adding real meaning to the parameter that needed it.

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 names a specific verb, resource, and lookup key: 'Look up a sales invoice by the `reference` you set on it.' The phrase 'the reference you set on it' signals a user-defined key, which clearly differentiates this from siblings like get_sales_invoice and find_sales_invoice_by_invoice_id that search by system identifiers. An agent can select this tool without opening 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 example 'e.g. a PO or project code' implies the natural use case: the agent has a customer-supplied reference rather than an invoice ID. However, the description never states when not to use it or names the ID-based alternatives, so the routing decision is left to inference rather than stated explicitly.

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