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

Annotations declare readOnlyHint=false, so an agent could assume the invoice is mutated; the description corrects this with 'This does not change the invoice,' which is exactly the kind of context annotations cannot convey. It still omits whether repeated submissions create duplicates (idempotentHint=false) or what authorization is required.

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 two most decision-relevant facts, the action and the no-mutation guarantee, are front-loaded, followed by a dense one-clause-per-kind list. Nothing is padded, though the telegraphic sentence fragments would read better as a compact list.

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 an output schema present, return values need no explanation, and the description supplies the conditional parameter rules the 0%-coverage schema lacks. The remaining gap is procedural context: no statement of prerequisites (e.g. invoice must exist in a draft state) or of what a recorded suggestion means for later acceptance.

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 17 parameters, so the description carries the entire burden and does so well by mapping each enum kind to its conditionally required fields (e.g. add_line needs description/quantity/rateMinor/unit). It leaves the always-required invoiceId and summary unexplained and does not state accepted values for unit or lateBasis.

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 ('Record a suggested change') and immediately scopes it with 'This does not change the invoice,' which separates it from the many mutating siblings. It does not, however, name or contrast itself with accept_invoice_change, the sibling that would otherwise be confused with it.

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 suggest a change versus applying it directly through siblings like place_line, set_line_quantity, offer_discount, or write_late_terms, even though the kind enum mirrors those tools. The per-kind requirement list implies what each kind does but never says when one is appropriate.

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