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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds substantial context beyond them: the 'no winner field and none can be derived' rule, the mandatory `caveat` naming what the data cannot settle, the clarification that Sato Score is openness/activity/verifiability rather than a safety or quality grade, and that every cell is read off live records rather than typed. These are real behavioral constraints an agent could not infer otherwise.

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 USE WHEN / NOT FOR, then returns, then the enforced rule, then an example — a sensible priority order with no filler sentences. Slightly redundant in stating the return shape twice ('RETURNS the SAME derived table' and 'RETURNS (json)'), which keeps it from a 5.

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 burden and does it well by enumerating the row labels and the JSON envelope keys, plus the caveat/rules contract. The only gap is that it says 'RETURNS (json)' without addressing the markdown-default response_format, leaving the default output form slightly ambiguous.

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 100% and both required slug parameters are documented with examples in the schema, so the baseline is 3. The description's example invocation ({ a: 'coinbase-agentkit', b: 'solana-agent-kit' }) largely restates schema examples, and it does not explain the response_format enum or that markdown is the default, so it adds little beyond the schema.

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 (compare) and resource (two directory listings) plus the exact scope: the axes Sato Hub tracks for both. It explicitly names the siblings it is not (onchain_agent_get_resource for single detail, onchain_agent_recommend_stack for ranked stacks), so an agent can route 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?

Opens with 'USE WHEN' giving the triggering question shape ('AgentKit or Solana Agent Kit?'), then 'NOT FOR' clauses naming two alternatives with the condition that selects each. This is explicit when/when-not/alternative guidance with nothing left to inference.

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