erc8004_feedback

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

Beyond the readOnlyHint and idempotentHint annotations, the description adds substantial context: it returns dry-run calldata, requires gas for broadcasting, encodes +1/-1 value, and links the receipt as proof. This gives the agent a clear mental model of the tool's side effects and outputs.

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 largely focused but includes promotional filler like 'FREE:', 'live on Base + 40 chains', and 'numguard joins the trustless-agents infra as a reputation provider'. These extra phrases do not aid tool selection and could be trimmed without losing essential information.

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 two well-described params and no output schema, the description covers the return value (args + calldata), the on-chain destination, the dry-run nature, and the value semantics. It is complete for a user to invoke correctly, though it omits edge-case handling like invalid receipts, which is acceptable.

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% with descriptions for both parameters. The description adds context by calling the receipt a 'numguard vcr/1 receipt' and identifying agent_id as the 'subject the verdict is ABOUT', which clarifies the role of each parameter 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 clearly states the verb 'build' and the resource 'ERC-8004 Reputation Registry giveFeedback call', with a specific outcome: return exact args and calldata. It distinguishes itself from the verify_* siblings by focusing on constructing on-chain feedback, not verification.

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 when to use: when you have a numguard receipt/verdict and want to make it portable on-chain reputation. It also clarifies this is a dry-run builder and broadcasting is the caller's step, contrasting with tools that execute on-chain actions. However, it does not explicitly name an alternative tool.

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