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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the mutation profile is covered. The description adds real business-rule context the annotations cannot: the operation is limited to draft invoices and setting a *different* description post-approval is refused. It still doesn't clarify what happens when the value is unchanged or how failures surface.

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?

Three short sentences, zero filler, with the primary constraint front-loaded and the alternative relegated to the end. Every sentence 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?

An output schema exists, so return values need no explanation, and the description covers lifecycle constraints and the alternative path. The remaining gap is parameter-level detail, which for a mutation tool with 0% schema coverage leaves it slightly short of fully self-sufficient.

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 description coverage is 0% across three required parameters, so the description carries the full burden but names none of them explicitly and gives no constraints (uuid format for invoiceId/lineId, 1-500 char limit). It only lets the agent infer 'invoice', 'line', and 'description' from the prose, which is weaker than the 3-baseline expected when the schema is silent.

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+resource ('Correct a line description') and a scope qualifier ('while the invoice is still a draft'), which singles it out from the sibling mutators like set_line_quantity or place_line. An agent can identify the operation without opening the 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?

Gives an explicit precondition (draft only), an explicit prohibition (after approval, a different description is refused), and routes to the correct alternative ('Use suggest_invoice_change with add_line for a different line'). When-to-use, when-not, and alternative are all present.

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