Metrics that moved

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

Annotations only cover read-only/idempotent/open-world, so the description carries the algorithmic burden and does: it discloses the median-rate phase partitioning, the ≥15% mean-difference rule, the three return buckets (`moved[]`, `not_moved[]`, `evaluation_failed[]`), and critically that the default threshold is uncalibrated and outputs are tagged `unvalidated_default`. That last point is a behavioral caveat an agent cannot get from the schema and would otherwise misread as a validated result.

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 and scope are front-loaded and the composition guidance closes it out, so ordering is good. It is a single dense block with several layered parentheticals, which slightly taxes readability, but every clause carries information an agent needs.

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?

An output schema exists so return-value explanation isn't owed, yet the description still enumerates the result partitions. Combined with the anchor semantics, candidate-set guidance, calibration caveat, and sibling hand-off, this is complete for an 11-parameter analytical primitive.

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 64%, and the description reinforces the two tricky parameters (anchor identity semantics, and the phase_gap_floor threshold with its calibration caveat) plus the rationale for the 100-candidate cap. It does not cover `step`, `environment`, or the three `customer_metrics_*` override parameters, which fall back to 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 first sentence gives a specific verb and resource ('deterministic filter on which customer metrics moved while an anchor was active') and immediately scopes it to the cross-pillar investigation flow. It names the sibling tools it composes with (`log10x_rank_by_shape_similarity`, `log10x_metric_overlay`), so an agent can tell it apart from the shape-similarity pass without opening either schema.

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?

Explicit positioning: 'First step of cross-pillar investigation' and 'the cheap deterministic cut that pares the candidate set before the more expensive shape-similarity pass', with a direct compose-with instruction. The agent knows both when to use it and what to call next, and the phrase 'no Pearson, no tier, no causal framing' rules out the things this tool is not for.

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