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

With no annotations, the description fully compensates. It explains data freshness ('as the 5-minute oracle_health pass last saw it'), the cache-based nature, the oraclePaused flag being advisory and not enforced, and the behavior of returning feed: null when the snapshot is past ceiling. It also clarifies the cadence semantics, leaving no ambiguity about the tool's 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?

The description is lengthy but information-dense, with no filler. It front-loads the core function and then expands on edge cases and related data. The structure is a bit run-on, but every clause contributes to understanding the tool's output and caveats. It could be split into shorter sentences, but the flow is logical and efficient.

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?

Given the tool's complexity (multiple output fields, several verdicts, null conditions, and a cross-reference to another tool), the description is thorough. It explains the return structure, the meaning of each verdict, the null handling, and the advisory nature of the paused flag. With no output schema, this description covers everything an agent needs to interpret results 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?

There is only one parameter, and its schema description already covers the three valid input types (symbol, token address, feed address). The description repeats this exact scope without adding extra constraints or format details. Since schema coverage is 100%, the description adds no additional semantic value beyond reinforcing the parameter's acceptable forms.

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 clearly states what the tool does: returns a Chainlink feed snapshot for a given ticker/address, including round data, oracle paused flag, deviations, and a verdict. It names specific fields and behaviors (e.g., feed: null on stale snapshot), making the purpose unambiguous and distinct from generic token queries.

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 usage context (when you need Chainlink feed data) but does not explicitly contrast with alternatives or state when not to use. It references 'rhxbt' as a separate tool carrying the premium board's read, but there is no direct guidance on choosing between them. Given the detailed scope, the intended use is clear, but exclusion criteria are absent.

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