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

With no annotations, the description carries the full burden and does so well: it declares payment-mode mutual exclusivity, that 'pending is not failure', that the same run should be repeated rather than rerun from scratch, and that a replacement purchase must not be created after a lost response. This is exactly the idempotency/retry context an agent needs. It stops short of covering error surfaces, rate limits, or what a successful response yields.

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?

Telegraphic and front-loaded: the core action leads, followed by param selection rules and then retry safety. Nearly every clause carries an instruction, though the staccato style makes the workflow rules slightly harder to parse on first read than plain prose would.

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-phase payment workflow with no annotations and no output schema, the description supplies the mode-selection logic, the retry/pending semantics, and state retention guidance. The main remaining gap is what the caller should expect back and how failures other than 'pending' manifest, but the critical call-time decisions are covered.

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 0%, so the description must compensate, and it does for the critical ambiguity: it explains when to populate authorizations versus transactions versus neither. run_id and access_token roles are only loosely implied by 'retain run_id/access_token', but the hardest parameter decision is fully resolved.

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+resource ('Execute or continue the SAME prepared graph') and implicitly distinguishes itself from pipeline_prepare (which prepares the graph) and pipeline_status (which it names as the read-only alternative). The word 'SAME' and 'prepared' make the relationship to siblings inferable, though the description never spells out what the graph actually accomplishes.

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?

Explicitly routes the agent: submit authorizations when the signed quote enables gas_sponsorship, otherwise buyer-signed transactions, and none for free steps, with a hard exclusion ('Never submit both payment modes'). It also names pipeline_status as the fallback when awaiting a pending result, giving both when-to-use and when-to-use-something-else.

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