One call: pick the most-trusted service for a need, fetch the data from it, and return the data together with that provider's trust score and its latest on-chain probe receipt as proof. Use when you want the answer AND a record of why the source was trusted. Scam / low-trust providers are never selected.
| Name | Required | Description | Default |
|---|---|---|---|
| need | Yes | The data you want, e.g. "current ETH price" or "weather in Singapore" |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden, and it does disclose the return payload shape (data + trust score + probe receipt) and the provider-selection policy (scam/low-trust never selected). It does not cover auth needs, cost/latency, rate limits, or what happens when no trusted provider is found, which are meaningful gaps for a tool with zero annotation coverage.
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?
Three short sentences, each doing distinct work: what it returns, when to use it, and the trust-selection guarantee. The core action is front-loaded with no filler.
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?
Since there is no output schema, the description correctly spells out what comes back (data, trust score, probe receipt), and with no annotations it supplies the key behavioral guarantee about provider selection. It is still silent on failure behavior when no sufficiently trusted provider exists and on cost/latency, leaving minor gaps.
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 100% and the single `need` parameter is already documented with concrete examples ("current ETH price", "weather in Singapore"). The description adds nothing about the parameter beyond framing it as the resolved need, so the 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 description names a concrete composite action: select the most-trusted provider for a need, fetch data from it, and return the data plus the provider's trust score and on-chain probe receipt. The phrase "One call" implicitly contrasts it with the multi-step path through siblings like find_service/check_trust/resolve_data_need. It stops short of naming those siblings explicitly, so the differentiation is inferred 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?
"Use when you want the answer AND a record of why the source was trusted" gives a clear selection condition, with the added constraint that scam/low-trust providers are never selected. However, it never states when NOT to use this tool or when to prefer the sibling tools (find_service, check_trust, resolve_data_need) instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.