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

Annotations cover the read-only/idempotent/closed-world profile, but the description adds substantive behavior the agent could not otherwise know: linked is null before POAScan's first read, staleness is exposed via links_stale/links_checked_at, and a warning object fires only when joining within 72 h without a link. It also discloses the domain rule that a link is needed only to swap and warns against requesting keys or off-network payment.

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?

No filler sentences, but the payload is delivered as one sprawling run-on sentence with nested parentheticals enumerating a dozen fields, making it hard to scan. Front-loading 'One poa1 address's wallet binding' is good; the rest could be broken into a short return-shape list and a separate usage line.

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?

There is no output schema, so the description must define return values — and it does so field by field, including null semantics, ordering ('newest first'), and the shareable lookup_url. An agent has everything needed to call it and interpret the response.

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?

Single required parameter with 100% schema coverage, including a base58 pattern and source hints ('as shown on POAScan or LabLeak'), so the schema carries the burden. The description's mention of 'One poa1 address' and the lookup_url template adds only marginal meaning beyond that.

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 and resource ('One poa1 address's wallet binding, public data only') and enumerates exactly what comes back (linked, vault, family, chains, tx lists, warning, lookup_url). It doesn't name how it differs from the similarly-shaped get_address sibling, so differentiation is implied rather than stated.

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?

Gives two concrete use cases ('check whether an Agent is ready to swap' and 'verify an external address'), which anchors when to call it. It lacks explicit when-not conditions or a named alternative tool, so it stops short of full routing guidance.

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