Live sample: for a fixed set of price feeds, whether each one would be rejected right now by a guard built on that feed's own measured cadence. Boolean verdicts only; ages, thresholds, the Chainlink-vs-Pyth spread and the revert selector are the paid GET /oracle-staleness.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly states that this is a 'live sample' returning 'Boolean verdicts only', which informs the agent that it will get immediate true/false responses without additional details. It also points to the paid endpoint for richer data. While it does not explicitly say it is read-only, the nature of a 'sample' implies a safe, non-mutating operation.
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 description is a single sentence with a semicolon and a dash, efficiently conveying the key points without redundant wording. It front-loads 'Live sample' and immediately explains the output. The structure is slightly dense but remains clear and acceptable for its length.
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 tool with no parameters and no output schema, the description is quite complete. It explains the tool's purpose, return type ('Boolean verdicts only'), and explicitly lists what is not included, while referencing the paid endpoint for those missing details. This covers the essential context an agent would need to decide whether to use this tool.
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?
The tool has 0 parameters, so the baseline is 4. The description adds extra meaning by explaining that the price feed set is 'fixed', which justifies why no parameters are available. This goes beyond the empty schema and clarifies the tool's behavior for the agent.
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 uses a specific verb ('sample') and clearly defines the scope: checking a fixed set of price feeds for rejection by a guard based on measured cadence. It distinguishes itself from sibling sample tools by explicitly stating 'Boolean verdicts only' and referencing the paid GET for additional details, making its unique purpose unambiguous.
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 description implies that this is a lightweight, free sample for quick boolean checks and that the paid GET /oracle-staleness should be used when ages, thresholds, spread, or revert selector are needed. However, it does not explicitly name alternative tools or provide a clear 'use this when' statement, leaving the usage context somewhat implied rather than directly stated.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct financial check (DAO governance, lending depeg, oracle staleness, Safe authority, vesting status), and the catalog serves as the index. No two tools overlap in purpose or output.
Five tools follow a clear 'noun_sample' pattern, but the catalog breaks the pattern with a prefixed name 'apix402_catalog', creating a minor inconsistency. Still, all names are snake_case and readable, so the deviation is small.
With only 6 tools, the set is compact and each tool represents a specific sample category plus a catalog entry point. This is an appropriate size for a preview-oriented MCP server.
The catalog lists all available checks, and the five samples cover key verticals (governance, lending, oracles, safe custody, vesting). The only gap is that paid endpoints are not exposed as MCP tools, but that is by design since payment occurs over HTTP.