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

Annotations already declare readOnlyHint=true, and the description reinforces the safety profile with 'never pays or changes an invoice', which is meaningful for an invoicing domain where mutation is plausible. It does not cover error behavior for a missing id or pagination-like concerns, so it stops short of full disclosure.

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?

One front-loaded sentence carries the capability, the boundary, and the endpoint reference. No filler or repetition of the title.

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 no output schema, the description usefully names what comes back (amounts, balances, payment status). It omits what happens when the id does not exist or belong to the caller, a minor gap for a single-parameter read.

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?

The path template GET /v2/invoices/{id} confirms the single id parameter's role, and schema coverage is 100% with a description telling the agent where to source the id. Little more meaning can be layered onto one integer identifier.

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?

Specific verb plus resource ('Read contractor invoices') and an enumeration of the fields surfaced (amounts, outstanding balances, payment status). It is distinguishable from arthur_list_invoices only implicitly via the /{id} path, not by an explicit statement contrasting the two.

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 'never pays or changes an invoice' clause clearly bounds when this tool is appropriate (inspection only, not mutation). It lacks an explicit pointer telling the agent to call arthur_list_invoices first to obtain the id, leaving that routing to the schema.

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