Find skew

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

Annotations already declare readOnly/idempotent, and the description adds substantial extra behavior: sampling is lossy (9 of 10 dominant events discarded), default thresholds are tagged unvalidated_default, and the output envelope surfaces observed_dominant_pct_distribution so the agent can judge calibration. This is exactly the kind of beyond-annotation disclosure that earns top marks.

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-loads the purpose, then layers differentiation, the Stage 1 input contract, and calibration caveats. It is dense and somewhat long, with a quoted example that is illustrative but adds bulk; still, nearly every sentence carries information, so only minor trimming is warranted.

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?

With an output schema present, the description need not restate returns, yet it still explains the key envelope field (observed_dominant_pct_distribution) and references the agent behavior contract doc. Given a 5-param tool with a required events array and calibration-heavy defaults, everything an agent needs to call it correctly is present.

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%, so the baseline would be 3, but the description adds meaning: it explains the calibration caveat behind min_concentration (0.6 floor) and sample_n (1/10), and points the agent to threshold_audit for judging whether the defaults fit the dataset. That is genuine added value over the schema text.

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 behavior: identify patterns where one slot value dominates a field (>=60% by default), with a concrete example of the finding it produces. It explicitly differentiates itself from analyzer field histograms, explaining that dominance is measured within the structural pattern rather than globally, so an agent can tell it apart from siblings without opening schemas.

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?

Gives clear usage context (surface sampling opportunities, Stage 1 accepts events as a paste array shaped like log10x_resolve_batch) and contrasts the mechanism against analyzer field histograms. It does not state an explicit when-not or name a preferred alternative for overlapping cases, so it falls short of a 5.

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