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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world. The description adds genuine behavioral context beyond them: the mark persists regardless of later invoice-system state, the deal timeline records the signed-in person as the actor, and downstream automation ("the job that gets the deal paid") acts on it immediately. It is consistent with idempotentHint=true, though the phrasing is somewhat impressionistic.

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?

Purpose is front-loaded in the opening clause, and each subsequent sentence carries information (durability, attribution, side effect, refusal). The phrasing is somewhat stylized and indirect ("the job that gets the deal paid looks at it now"), which slightly obscures the payload but wastes little.

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?

For a one-parameter mutation tool with no output schema, the definition supplies purpose, semantic nuance, side effects, attribution, and refusal conditions, while annotations cover the safety profile. Nothing an agent needs to call it correctly is missing.

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% and the sole parameter's origin is documented ("from read_the_money_of_a_deal"). The description adds no syntax or format detail beyond the schema, so the baseline of 3 applies when the schema does the heavy lifting.

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 ("Mark an invoice of a deal as paid") and disambiguates the write from the read sibling by describing the underlying scenario (a payment that reached the company outside its invoice system). It never explicitly contrasts itself with siblings like read_the_money_of_a_deal or close_the_job_that_gets_a_deal_paid, so full sibling differentiation is absent.

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 a clear usage context (an out-of-band payment) and an explicit exclusion ("Refused for an invoice that was cancelled or never made"). It stops short of naming alternative tools for those excluded cases, so it is a clear context rather than a full when/when-not/alternatives routing.

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