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

Annotations already establish a read-only, idempotent, non-destructive profile, and the description goes well beyond them: it discloses the confidence cap (0.60), the absence of a 'high' tier, the meaning of tier:'unknown', the mutual exclusivity of p_cause/p_unknown, and the no-causation reporting discipline. The only gap is it doesn't describe pagination or response envelope shape, though it does cover the semantic fields.

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 is front-loaded in the first sentence. The body is dense and every paragraph carries a distinct semantic payload (render discipline, the three numbers, tier semantics, request shape). It runs long, but with no output schema the verbosity is largely load-bearing rather than 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?

With no output schema, the description must carry the full return-value burden — and it does, defining change_evidence, attribution_completeness, p_cause/p_unknown, tier, explained_day, and explanation.sentences, plus the API endpoint it mirrors. Nothing an agent needs to call or interpret this tool is missing.

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 a 3 is the floor, but the description adds real meaning: 'dimension + value name the slice, optional cost_source_id narrows it, and exactly one of day or range says when' — the mutual-exclusivity constraint is not stated in the schema. It also explains the range→explained_day narrowing behavior, which the schema only hints at.

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 and resource ('Explain a specific cost change') and immediately enumerates the three things it returns: which timeline events line up, how strongly, and how much Plutus could account for. It also distinguishes itself from the sibling list_anomalies by scope ('any point on a cost chart — not limited to anomalies the detector flagged').

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?

Explicitly says when to use it ('ask this about any point on a cost chart') and names the alternative for the flagged-anomaly case ('use list_anomalies for those; each already carries the same explanation'). It even governs downstream behavior with 'RENDER explanation.sentences AS WRITTEN', which is strong usage guidance.

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