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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false), so the bar is lower. The description still adds meaningful value: it explains that a draft has no accounting impact, carries no number, and reaches nobody until confirmed, plus a required-permission note (Cotlet API key). What is missing is whether re-creation or failure modes exist, but the key lifecycle semantics are disclosed.

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 purpose and lifecycle are front-loaded in the first two sentences, followed by the confirmation route and permission requirement. Some phrasing is slightly indirect ('does not wait for your OK'), but overall the paragraph is short and each sentence carries informational weight.

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?

Given a mutation tool with no output schema, the description supplies the lifecycle context, the follow-up step, and the authentication requirement. It could more explicitly state whether the returned ID is needed for downstream calls or whether creating a duplicate draft is possible, but it is substantially complete for correct invocation.

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 100%, so the schema already documents all five parameters. The description restates the return value ('ID and totals') but adds nothing about parameter formats or relationships beyond the schema's own descriptions. Baseline 3 is correct when coverage is this high.

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 (create) and resource (customer invoice in Draft status), and explicitly distinguishes the draft state from the final one by naming the sibling post_invoice as the follow-up. An agent can tell this apart from odoo_post_invoice without opening either 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?

Names the follow-up action explicitly ('Confirm it with post_invoice'), giving the agent a clear next-step path. However, it does not state when to prefer this draft route versus directly posting, nor does it set a negative condition for skipping it.

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