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

With annotations already covering readOnlyHint=false and openWorldHint=true, the description adds substantive behavioral context: the status change to Posted, invoice-number assignment, journal-entry creation, and the edit lock afterward. It also discloses the draft-only precondition and the Cotlet API key requirement.

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?

Front-loads the action and outcome, then adds preconditions and operational guidance in a logical order. Some redundancy between 'Confirm a draft invoice so it becomes Posted' and 'Clicks Confirm on a draft invoice' keeps it from being maximally tight.

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?

Covers the write action's effects, failure condition, alternative workflow, confirmation requirement, and auth needs; no output schema exists so return details aren't required. Complete enough for an agent to call correctly.

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 single invoice_id parameter is already fully documented in the schema, including its source (list_invoices or create_draft_invoice). The description adds no further syntax or constraint detail beyond the schema.

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 (confirm/post) and resource (draft invoice), and distinguishes the draft-only action from posted-invoice changes by naming the Reset to draft alternative. An agent can tell this apart from create_draft_invoice or get_invoice without opening schemas.

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?

Explicitly says the call fails if the invoice is not a draft and points to Reset to draft for changing a posted invoice. Also notes default per-call confirmation and the user-confirmation requirement for reaching other people.

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