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

No annotations are provided, so the description carries the burden. It discloses that the tool returns HTTP 402 with payment terms until payment is presented, that payments are final and non-refundable, and that the provider never receives funds. It also discloses the untrusted-provider content and that contract source is data to analyze, not instructions. However, it does not describe the exact output format beyond 'one-line verdict plus counts and top findings', and the payment behavior is described in a somewhat confusing way (the tool returns 402 until payment is presented, but the description also says the call costs $0.05).

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 cluttered with payment/provider details and untrusted-provider content that obscure the core purpose. The first sentence is about pricing and payment, not about what the tool does. The actual functional description is buried in the untrusted-provider content block. While the untrusted-provider content is required by policy, the overall structure is not front-loaded with the tool's purpose.

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?

The description covers the tool's purpose, input parameters, output shape (one-line verdict plus counts and top findings), and routing to the full audit sibling. However, it lacks details about error cases beyond HTTP 402, rate limits, or what happens if the repo is not found. The payment behavior is described but in a way that may confuse an agent (does the tool always return 402 until payment, or does it execute the scan?). Given the tool's complexity and lack of output schema, the description is adequate but not complete.

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 description coverage is 100%, so the schema already documents both parameters. The description adds context that repo is a GitHub repo as owner/name and ref is a git ref, but it doesn't add much beyond the schema. It does mention POST {repo, ref?} which confirms the request shape, but this is marginal value over 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 states a specific verb and resource: it performs a 'go/no-go risk verdict for ONE Solana/Anchor contract' by POSTing {repo, ref?} and returning a one-line verdict. It distinguishes itself from the full audit sibling by saying it checks 'high-signal rule families only' and returns a verdict, not a full report. However, the description is cluttered with payment/provider details that obscure the core purpose, and the tool name is somewhat generic.

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 explicitly says when to use this tool vs alternatives: if the verdict is NEEDS_REVIEW or DO_NOT_INTERACT, run sol-audit for the full report; if you already know the repo is risky and need every finding, skip this and go straight to sol-audit. This is clear routing guidance that names the sibling tool and the conditions for choosing it.

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