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

Annotations already establish read-only, idempotent, non-destructive and closed-world, so the description's job is to add context, and it does: it discloses that access is free with no key required and that an unrecognized family degrades to the audit's published list rather than erroring. It does not describe response shape or ordering, but the metric-level disclosure (five-session returns, control comparison) is substantive added 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?

Three sentences restate the same object — 'public record', 'graded public record', 'published forward record' — with near-identical metric lists (days graded, hit rate, misses, worst days appear twice). The lead is a rhetorical question rather than a verb+resource statement, so the definition is inflated and not front-loaded.

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 one-parameter read tool with full annotation coverage and no output schema, the description carries the return-value burden and does so by listing the reported metrics and the family semantics. The remaining gap is minor: no statement of ordering, timeframe, or how many 'worst days' are returned beyond the stated three.

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 schema only says 'top_decile or ready', so the baseline would be 3; the description goes further by glossing the families semantically (top_decile = opportunity, ready = entry quality) and by defining the unknown-value behavior. That meaning is not recoverable from the schema alone.

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 names a concrete resource (the graded public track record of a named score family) and enumerates its contents: days graded, hit rate, average excess over control, last day graded, misses and worst days. That is enough to tell it apart from the market-data siblings, but it never explicitly contrasts itself with them, and the repeated framing ('public record', 'graded public record', 'published forward record') blurs the single purpose rather than sharpening it.

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 when-to-use or when-not-to-use guidance and no named alternative among the ~45 siblings. The only situational hints are incidental ('Free; no key needed') and the fallback note that an unknown family returns the published list, which is a behavior fact rather than usage guidance.

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