signal_divergence

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

No annotations are provided, so the description carries the burden. It discloses the ranking mechanism (within-position percentile normalization) and what a large gap means in both directions, which is genuinely useful. It does not cover permissions, cost, or whether results are cached/live, and with an output schema present the return shape is handled elsewhere.

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?

Front-loaded with the core purpose in one sentence, then mechanism, then interpretation, then args. The percentile-rank paragraph is slightly long but earns its place by preventing misreading of the gap sign. No filler.

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 5-param, zero-required tool with an output schema, the description supplies the conceptual model needed to call it correctly: what gets compared, how it's normalized, and how to read the sign. It leaves only league_id_ undocumented and doesn't clarify whether week=0 is always 'current NFL week' vs. league week, a minor gap.

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 description coverage is 0%, so the description must compensate. It documents three of the five parameters with real semantic meaning — min_evidence (evidence threshold), gap (minimum percentile gap), limit (rows per direction) — each with a sensible default. It omits week semantics beyond the 0 default and ignores league_id_ entirely, hence 4 rather than 5.

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 exactly what it does: surfaces where the agent's own signal and Sleeper's projection disagree most, using within-position percentile ranks. Distinguishes itself from siblings like player_signal and usage by describing a comparative gap rather than a single source metric.

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 explains the interpretation of positive vs. negative gaps (why you'd use it) but never states when to choose this over player_signal/usage/breakouts, nor any prerequisites. Usage is inferable from the output semantics, so 3 is fair.

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