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

Beyond the annotations, it discloses that the tool reads only call material with no network/fetch/money movement, that it is paid at 0.10 USDC per call with 10 free signed-wallet calls per 30 days, that X-Wever-Wallet-Proof must bind to the exact JSON arguments and route, and that it returns an Ed25519 signed receipt. This is rich behavioral context the annotations do not carry.

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 purpose and required design elements are front-loaded, followed by report contents, verdicts, endpoint, payment, and contract links. It is dense and long but each block carries distinct information; minor redundancy in the payment/contract tail keeps it from a 5.

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 complex nested-input tool with no output schema, the description explains the verdict set (settles_unchecked, enforcement_unverified, record_incomplete, enforced) and what the signed report names, which is enough for an agent to call it correctly. It stops short of describing the full report structure, but the verdict enumeration largely compensates.

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?

With 60% schema coverage and nested objects, the description adds real meaning: it explains that checks carry where each runs and what a failure does, that the cap has a scope and what counts toward it, and that paths cover retry/split/reorder/manual. It maps the design semantics onto the parameters rather than restating 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 a specific verb and resource ('submit a payment firewall's design') and enumerates exactly what the design must contain (checks with run locations, cap with scope, settlement paths, records). This is far more specific than the sibling check tools and lets an agent distinguish it from generic payment-policy checks.

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 implies the use case (submitting a firewall design for verification) and states the read-only, no-side-effect nature, but never explicitly says when to choose this over siblings like wever_payment-policy-check or wever_spending-policy-check, nor any prerequisites beyond the wallet proof.

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