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

The destructiveHint annotation only signals 'this mutates'; the description specifies exactly what is destroyed ('line_items ... replace every existing line') and scopes the blast radius ('only the fields you pass change'). It also confirms no side-effect sending occurs, which the annotation does not convey.

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 dense sentence carries the verb, the partial-update contract, the destructive caveat, the no-send guarantee, and the endpoint. Every clause earns its place and the most consequential fact (line replacement) is stated early.

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 17-param mutation tool with no output schema, the description covers the essentials an agent needs to call it safely. Minor gaps remain: no mention of what the call returns, and no auth/permission prerequisites, though nothing required to invoke it is missing.

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 100%, so the baseline is 3, but the description adds a semantic the schema only half-captures: partial-update semantics ('only the fields you pass change') for all 17 parameters and the replacement behavior of line_items. That is real value beyond the field-level descriptions.

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 and resource ('Edit an invoice') and distinguishes itself from sibling write/read tools like create_invoice and get_invoice. It even names the underlying endpoint (PUT /api/v1/invoices/{id}), leaving no ambiguity about what the tool does.

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?

'Does not send anything' implicitly routes the agent away from send/email siblings (e.g. invoiceninja_email_invoice) and clarifies this is a data-only edit. It gives clear context for use but never names an explicit alternative or a when-not-to-use condition.

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