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

Annotations already declare this is a non-readonly, non-destructive, non-idempotent write; the description adds real context beyond that by disclosing that two fiscal documents are produced and that the operation is simulated first. It does not explain how the simulation is later confirmed or what happens to the storno if the second document fails, which is material for a fiscal 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?

Dense, front-loaded and free of filler; the core mechanism and the simulation caveat come in the first two clauses. The parenthetical CIF example slightly interrupts flow but earns its place by making 'corrected client' concrete.

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, the description need not explain return values, and it covers the two-document outcome, the simulation-first semantics, and the demo-data scope. The remaining gap is the lifecycle after the proposal, which an agent needs in order to finish the correction.

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 only 29%, so the description must compensate. It usefully explains that client and lines are the corrected elements (with the CIF example and 'default: original lines' being schema-side), but it never mentions series/number as the required identifiers of the original, nor reason or new_series.

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 (correct/reissue) and resource (an already-issued invoice) and explains the mechanism: a storno with negative lines referencing the original plus a replacement invoice. This distinguishes it implicitly from invoices_issue and invoices_cancel, though it never names either sibling to draw the boundary explicitly.

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?

'Propose correcting an invoice already issued' gives an implied trigger case, and the CIF-vs-person example clarifies the kind of correction intended. However, there is no explicit guidance on when to use invoices_cancel or invoices_issue instead, nor what to do after the proposal (commit via manage_action?).

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