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

With no annotations, the description carries the full behavioral burden and does so well: it discloses the auth requirement (only the on-chain owner's signature; EIP-191/personal_sign), replay protection (a nonce works once), the two-phase protocol, and the concrete side effects on the write path (stores enrichment, probes the first endpoint, queues for the harvester, returns new readiness).

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?

Three sentences, front-loaded with purpose, then the two mode-split flows, then the constraint on accepted signatures. Dense but every clause (nonce freshness, EIP-191, harvester queueing) carries information; nothing is filler.

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 mutation tool with no annotations, no output schema, six params and a nested data object, the description covers the protocol, side effects, and auth constraints well. It stops short of explaining chain_id and confirmation/error behavior an agent might need on the write path, but the omission is minor relative to what is provided.

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 only 17%, so the description must compensate. It adds meaning for the enrichment payload fields (card_url, endpoints, skills, classes) and the signature/nonce/expires flow, but leaves agent_id and chain_id unexplained and gives no format detail for the signature string itself, so the gap is only partially closed.

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 (Enrich) and resource (an agent) plus the exact owned fields (card URL, endpoints, skills, class opt-in), and qualifies it as the ERC-8004 owner action. This clearly separates it from siblings like taifoon_agents_register and taifoon_register, which handle registration rather than post-registration enrichment.

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 two-mode flow (no signature -> get message to sign; with signature/nonce/expires -> store) provides real invocation context, but it never states when to prefer this over sibling tools such as taifoon_agents_register or taifoon_agent_readiness, nor any prerequisite beyond being the owner. Usage is implied through the flow description rather than explicitly routed.

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