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

Annotations already cover read-only/idempotent/non-destructive/open-world, but the description adds real value beyond them: data freshness ('stored reads only'), cost model ('free, never spends a scan'), and the meaning of each verdict, including the explicit warning that 'unknown' must never be treated as 'clear'. It stops short of covering staleness/expiry or error behavior.

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?

Purpose and output shape are front-loaded, and the dense clauses (verdict definitions, cost/freshness) each carry information. The second half is a long run-on sentence with heavy punctuation, which costs some readability.

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 no output schema, the description carries the return-value burden and does so: it defines the four verdicts, the reason structure (level/code/sentence, worst first), and the semantics of 'avoid' and 'unknown'. Combined with annotations covering safety, an agent has enough to call and interpret it correctly.

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 0% for the single required 'address' param, so the description must compensate. It does partly, by declaring the accepted address namespaces ('a Robinhood Chain 0x contract or a Solana mint'), which is meaningful guidance absent from the schema. It does not spell out the exact format/validation rules, keeping it from 5.

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 purpose: a single risk decision ('clear | caution | avoid | unknown') for a Robinhood Chain 0x contract or Solana mint, positioned as the agent's pre-buy risk step. The verb+resource+output are all named, so it is easy to tell apart from scan/record tools. It does not explicitly name a sibling alternative (e.g. rh_token_safety), which keeps it at 4 rather than 5.

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?

'For an agent's risk step before a buy' gives clear situational context for when to call it. 'Stored reads only, free, never spends a scan' implicitly distinguishes it from scan-consuming siblings (e.g. rh_scan_now), but no explicit when-not or named alternative is stated.

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