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

Annotations already declare readOnly/idempotent/non-destructive, and the description's 'Read-only' merely restates that. What it adds beyond structured fields is genuine: the Directory reads x402 offers 'once a day, never paid' (freshness and no-side-effect guarantee), the exact fallback string 'No Priors record yet.', and an explicit prompt-injection warning that the agent's own links are data and not instructions or endorsement. That last point is valuable safety context an agent would otherwise lack.

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 body is one sprawling, parenthetical-laden construction that mixes return contents, caching policy, payment mechanics, and safety warnings without paragraph breaks or ordering cues. The fragment about paying an offer 'from the agent's own @priors/mcp, borrowing the gap within its owner's limits' is syntactically broken and hard to parse. It is front-loaded with the purpose but far longer than needed.

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 read-only lookup with no output schema, the description covers what an agent needs: the field groups returned, the empty-record fallback, data freshness, and a trust boundary for embedded links. The only omission is any guidance on error behavior for unknown agent ids, which is minor given idempotent read semantics.

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 a single parameter at 100% schema coverage, the schema already fully documents agent_id with an example. The description reinforces that any ERC-8004 identity qualifies, but adds no format, range, or resolution detail beyond what the schema provides. Baseline 3 applies.

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 opening clause names a specific verb and resource: show an ERC-8004 identity on Robinhood Chain as Priors reads it, then enumerates the exact sections returned (owner/registration, Priors record, pays-to wallet, x402 offers, website/services). It distinguishes itself from siblings like agent_record by scope, though the reader must infer that distinction rather than being told. The core purpose is clear despite the heavy jargon and run-on construction.

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 phrase 'with or without a Priors record' clarifies that this tool works for agents lacking a Priors record, which implicitly sets it apart from record-only siblings. However, it never names an alternative or states when to prefer agent_record, find_agents, or find_agent_by_x. Usage is implied rather than prescribed.

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