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

Annotations declare non-read-only, open-world, non-idempotent, non-destructive; the description adds genuinely new facts: a 1-credit cost with a 40-page ceiling, that confirmation/delivery-report/thank-you mail are sent to 'email', and that the result distinguishes sent vs. scheduled vs. unpaid. It does not explain irreversibility of a sent fax or failure/refund behavior, which a paid mutation of this kind warrants.

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 purpose, cost and the confirmation requirement, then the document options, then the outcome semantics. Dense but every sentence carries decision-relevant content; the document enumeration is long but mirrors eight real parameters, so the length is largely earned.

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 an 8-parameter, nested-object, no-output-schema mutation tool, the definition covers cost, required user confirmation, all input routes, scheduling window (present in schema) and the semantic shape of the result, so an agent need not guess at return values. Minor omission: no guidance on retry/idempotency after an ambiguous result, which matters given idempotentHint=false.

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 baseline is 3, but the description goes further by explaining the choice logic between the four document parameters and their origin (upload_id comes from create_upload_link, file is auto-populated by ChatGPT, base64 is only for very small files). That is decision-relevant meaning beyond the field descriptions.

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 ('Sendet ein echtes Fax über SofortFax') and immediately distinguishes itself from the read-only siblings by naming the price model and the triggering of a real-world action. An agent can tell it apart from create_upload_link (a prerequisite) and get_fax_status (the follow-up) without opening a 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?

Gives clear operational context: obtain user confirmation of number, document and schedule first, and routes file input among four mutually exclusive sources, explicitly pointing to create_upload_link as the preferred path for on-device files. It stops short of naming when to prefer send_fax over the sibling list in a workflow sense, but the required preconditions are explicit.

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