Is an agent's newest payment in character (free, shadow)

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

Annotations already establish readOnly, idempotent, non-destructive, non-open-world semantics, but the description adds genuine context beyond them: shadow mode means nothing is blocked, levels are non-authoritative patterns for humans, and every figure carries a measurement time and definition id. It also discloses the shape of what comes back (fired reasons, 30-day notable/major count, market rates). It stops short of describing caching or latency behaviour.

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?

Purpose is front-loaded, but the body is a single sprawling sentence with a deeply nested parenthetical list of eight signals, which is hard to parse on first read. The signal taxonomy is arguably definitional rather than decision-relevant for selecting the tool. Size is defensible for a tool with no output schema, but structure is weak.

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?

There is no output schema, so the description must explain the return values, and it does: the score, the reasons that fired, the notable/major count over 30 days, the market rates, the none/notable/major levels, and the measurement time and definition id on every figure. Given one enum-free parameter and read-only annotations, nothing an agent needs to call this correctly is missing.

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 `agent` property already documents accepted forms (token id, act_8453_N, slug, bound wallet), so the schema carries the parameter burden. The description adds no syntax or format detail beyond that. Baseline 3 is correct when the schema does the heavy lifting.

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?

States a specific verb and resource: it scores an agent's newest counted payment against that agent's own earlier payments for out-of-character signals. The parenthetical enumerates the exact signals in the v2 definition, so an agent knows precisely what the output measures. It does not name any sibling (e.g. pay_check, detections, since_last) to differentiate scope, so 4 rather than 5.

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?

There is no statement of when to call this versus the many sibling tools such as pay_check, detections, or since_last, nor any prerequisites or exclusions. The only interpretive note – that a level is a pattern for a human to read, never a verdict, and shadow mode blocks nothing – guides how to read results rather than when to select the tool. Usage is left entirely to inference.

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