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

Annotations cover only the safety/idempotency profile; the description layers on auth requirements (Bearer membership claim or x402 USDC payment on Base), latency and retry guidance (10-20s cold, do not retry), per-member/per-day caps, refusal semantics naming the cap and its 00:00 UTC reset, and caching behavior. This is exactly the operational context the structured fields cannot express, and it is consistent with idempotentHint=false.

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?

Front-loaded with the member designation and the core action, then layered with auth, cost, latency, and cap caveats in compact clauses. Dense but nearly every sentence carries an operational constraint; slightly long for a one-parameter tool.

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 slow, metered, paid read with no output schema, the description covers everything an agent needs: authorization options, time cost, retry policy, quota mechanics, refusal shape, and cache short-circuit. No meaningful gap remains.

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?

There is one parameter at 0% schema description coverage, and the description never explains its format or how it resolves (e.g., checksummed address vs. ticker). It only implies 'one contract' is passed. The implied meaning is adequate to call the tool but adds little beyond the schema field name.

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 ('read one Robinhood Chain contract FRESH') and scopes it against the sibling trigger ('when rh_token_safety said found=false or the stored read is stale'). An agent can distinguish this from rh_chain_stats or rh_token_safety without opening any schema.

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 both when-to-use (after rh_token_safety returns found=false, or when the stored read is stale) and an implicit when-not ('a read from the last few minutes is served from the store without spending'), which tells the agent to skip the call entirely. The alternative path is named explicitly.

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