signal_grades

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety/scope profile is covered. The description adds that it only grades windows that have 'finished' and mentions Yahoo ownership data as 'our lead,' which is useful context. But it doesn't describe return shape or cost, and with the annotations doing the heavy lifting a 3 is appropriate.

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?

One dense but well-structured sentence with no filler; the definition of 'hit' is front-loaded in parentheses and both reported outputs are named. Slightly long but every clause carries information.

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 zero-param read-only reporting tool, the description covers what it grades and what it returns at a high level. With no output schema, it could be more explicit about the return structure (e.g., per-kind breakdown format), leaving a gap an agent would have to probe.

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?

Zero parameters, so per rubric the baseline is 4. The description correctly implies the tool takes no inputs by describing a self-contained reporting operation.

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 (grade) and resource (signals with a finished 14-day window), and describes the two outputs it reports (hit rate by kind/confidence, Yahoo ownership movement). It's distinguishable from siblings like grade_decisions or prediction_calibration, though it doesn't explicitly name the comparison.

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 parenthetical '(hit = production moved as the signal said)' clarifies what 'grade' means here, and the 14-day-window condition is a usage boundary. But there's no explicit when-to-use/when-not vs grade_decisions or prediction_calibration, which an agent might confuse it with.

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