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

Annotations only state readOnlyHint=false, openWorldHint=true, idempotentHint=false, destructiveHint=false. The description adds substantial behavioral context: the server verifies payment covers the actual content price, refund policies (automatic for card/Checkout and Stripe machine payments, manual for on-chain), the specific error code -32042 for payment challenge, and the use of a real fax carrier. These go far beyond what annotations provide.

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 description is dense but well-organized: a single purpose sentence followed by a detailed explanation of payment methods, verification, and refunds. Every sentence contributes critical information; there is no fluff. The structure uses clear separation of the two payment paths, making it readable despite its length.

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 the tool's complexity (5 params, two payment flows, error handling, refunds) and lack of output schema, the description covers all essential aspects an agent needs to call it correctly: how to initiate both payment methods, what the server checks, how refunds work, and the retry mechanism. It is complete for a fax-sending operation.

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 descriptions cover 100% of parameters, so the baseline is 3. The description adds extra semantics for payment_id ('Omit to pay autonomously', source from create_fax_payment, credential handling) and clarifies the distinction between cover_text and document_url ('cover_text to fax instead of a document'). This enriches understanding 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?

The description clearly states 'Transmit a fax' – a specific verb and resource. It distinguishes from siblings by describing the payment flow that ties to create_fax_payment and mentions the server's verification and refund behavior, which sets it apart from get_fax_quote and get_fax_status. The purpose is unambiguous.

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?

The description gives explicit guidance on how to use the tool: two payment methods (human-in-the-loop via payment_id and autonomous machine payment without it), with detailed instructions on how to handle the payment challenge and retry. It clearly references create_fax_payment as the source of payment_id, indicating the intended sequence. It does not explicitly mention alternative tools for exclusion, but the context is sufficient.

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