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

The description goes beyond the readOnly/idempotent annotations by disclosing the one-hour validity, bearer nature, and that no-arg calls return the general settlement document. The verb 'create' is slightly ambiguous with readOnlyHint, but the 'returns' language frames it as generating an ephemeral signed document rather than a persisted resource.

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?

Three sentences, no filler. The central behavior and expiry are front-loaded, the exclusion rule follows, and currency/no-arg behavior closes with practical detail.

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?

With an output schema present and annotations already covering safety/idempotence, the description supplies the key decision-relevant context: when not to call, what no-args does, and what currency means. Nothing essential for correct invocation is left unspecified.

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 schema already describes the parameters. The description adds practical meaning: 'USDC for Base Pay or ETH for exact wei', the no-product argument variant, and confirmation of which product types map to which catalog shelves.

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 names a specific action ('Create or refresh') and a concrete resource ('one-hour signed bearer offer'), and scopes it to skill, bundle, audit, or fix. This makes it easy to tell apart from sibling tools such as get_fix/get_skill, which return catalog content rather than payment instruments.

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 explicitly states when not to call the tool ('Do not call this after a paid search_fixes result or an unpaid get_fix/get_skill result') and why (those responses already include payment rails). It also gives selection guidance for currency and defines the no-argument fallback.

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