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

Annotations only provide basic flags (readOnlyHint false, idempotentHint false). The description adds deep behavioral context: payment is USDC on Solana only, the founder must use a self-custody wallet, nothing files until confirmation and human review, refund policy, and the 48-hour confirmation link. It even warns against exchange withdrawals. This far exceeds the annotation coverage without contradiction.

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 lengthy but densely packed with essential operational details for a complex flow. It is front-loaded with the core purpose and then structured sequentially (first call, second call, payment, exclusions). While not terse, every sentence contributes; minor redundancy exists (reiteration of USDC-only) but it's justified for emphasis.

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 (7 params, nested objects, two-call protocol, payment nuances) and that the output schema exists (though not shown), the description covers all necessary context: prerequisites, consent handling, payment mechanics, retry behavior, and restrictions. An agent would have everything needed to execute the correct multi-step flow.

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?

The schema already covers 100% of parameters with detailed descriptions, so the baseline is 3. The description adds value by explaining lifecycle semantics: which parameters belong to the first call vs second, the meaning of consent.version (from formation.requirements), and the idempotencyKey reuse rule. It doesn't add syntax details but clarifies usage context 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 opens with the exact outcome: 'Create the founder's formation order and get a USDC (Solana) payment request' and differentiates it from siblings (formation.handoff validates, this one creates and takes payment). It also notes exclusions like the tax-ID add-on and the no-sign-in aspect, making the tool's role unmistakable.

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 lays out a precise two-call flow: first call with complete draft+consent+idempotencyKey, second call with orderId/trackingToken/acceptPromise. It states when to use it (after reading acknowledgements), when not to (tax-ID add-on), and how to retry (reuse idempotencyKey). It also gives the external alternative for validation (formation.handoff), leaving no ambiguity.

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