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

Beyond the annotations (readOnly, openWorld, idempotent, non-destructive), the description adds valuable behavioral context: hourly recomputation, payload includes its own computed_at to quote instead of the request time, counts are counts not rates, entry is market cap at logging, and the index is limited to PumpPill's observations. This meaningfully clarifies the tool's data freshness and interpretation.

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 front-loaded with the core purpose and metric list, followed by essential caveats about quoting and interpretation. Every sentence carries substantive information; no filler or repetition. The two-paragraph structure is efficient for the amount of critical context provided.

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 and no parameters, the description serves as the primary guide to what the tool returns and how to interpret it. It enumerates included metrics, clarifies the time to attribute, and explains limitations. An agent would know exactly what to expect and how to handle the response, making it complete for this tool's complexity.

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 zero parameters, so the empty schema already covers everything (100% coverage). The baseline for 0 parameters is 4, and the description adds context about the payload contents (e.g., computed_at, metrics), which further supports interpretation even though it does not describe input parameters.

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 the tool measures chain statistics from PumpPill's index, listing specific metrics (tokens seen, outcome counts, doubling/10x thresholds, $100k crossing, tokenized stock quotes). This goes beyond a tautology and distinguishes it from siblings like rh_stock_pairs or rh_token_safety, which target specific token data.

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 by describing the tool's scope (chain-level statistics, hourly recomputation) and notes the index covers 'what PumpPill has seen rather than everything that exists,' providing a context cue. However, it does not explicitly advise when to use this tool over alternatives or when not to use it, leaving selection partly to inference.

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