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

With annotations covering only readOnlyHint/openWorldHint, the description carries real weight: it discloses the credit-spend model, that any key draws on one balance, that repeat fetches are free, and the exact failure contract (HTTP 402, code PAYMENT_REQUIRED, link to buy credits). That is far more than the annotations provide and is exactly what an agent needs before triggering a paid action.

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-loaded with the action and formats, then the billing and error semantics. Dense but every clause carries information; the parenthetical aside about agents reading Markdown is mildly redundant with the schema but not wasteful.

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 two-parameter tool with no output schema, the description covers the return artifact (the document in the chosen format) and the payment/error outcomes. It does not say what happens if the deal is not yet agreed or the dealId is invalid, a minor gap given the paid-fetch path is well documented.

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 both parameters are already documented, including the format enum and md default. The description adds only a soft recommendation ('Markdown by default: agents read it best') that largely restates the schema's own 'md or html for agents' note, so the baseline 3 applies.

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 opens with a specific verb and resource ('Download the agreed contract') plus the exact output formats, which cleanly separates it from sibling generate_contract (which produces the contract in the first place). An agent can tell what it gets and in what forms without opening the 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?

It gives clear situational context: the contract must already be 'agreed', negotiation is free, and the fetch is the point of payment, with later fetches free. It does not explicitly name alternatives (e.g. generate_contract or get_deal) or state the precondition as a when-not rule, so it stops short of a full routing instruction.

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