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

With no annotations, the description carries the transparency burden and does substantial work: it enumerates return values, verdict options, the methodology weighting, and the confidence floor. It strongly implies a read-only computation, though it does not explicitly state read-only status, rate limits, or behavior for nonexistent agents.

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 dense and well structured: purpose, return fields, methodology, and input. The '[FREE]' label is useful for cost signaling, but 'invention #3985' is unnecessary noise and the opening is slightly redundant with the tool name.

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?

The description covers inputs, output semantics, verdict values, and the behavioral principle behind the score, which is complete enough for an analysis tool. Minor gaps include explicit when-to-use guidance and edge-case handling for unknown subjects, but NO_SIGNAL partially addresses that.

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 0%, so the description must compensate. It does by clarifying that 'subject' is an AgentWorld agent name or id, adding meaning beyond the bare string property in the schema. It stops short of specifying formats or case sensitivity, but this is sufficient for a single parameter.

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 analytic action ('separates stable USDC revenue from bursty, gameable spikes') paired with a clear resource ('an AgentWorld agent'). Its focus on volatility-adjusted revenue stress-testing is distinct from sibling trust, solvency, or ambiguity tools, so an agent can tell when it applies.

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 its use case: verifying whether an agent's revenue is stable rather than spike-dependent, and notes that reputation cannot be inflated by one lucky payout. However, it never explicitly states when to prefer this tool over alternatives like get_agent_trust_pulse or get_solvency_ratio, nor does it provide exclusions.

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