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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description nonetheless adds real behavioral context: this is diagnostic-only, it does not establish a cause, and neither input record is verified as correct — important caveats an agent would otherwise assume away.

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?

Core computation is front-loaded in the first sentence, followed by limits and routing guidance. Slightly padded by the trailing 'Diagnostics-tier tool.' fragment, which restates what prior sentences already conveyed, but overall efficient.

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 6-parameter, nested-object tool with no output schema, the description conveys the outputs (projection, residual, per-field contributions) and the input pairing needed. It stops short of describing the return structure or how blueprint and inline rules interact, which is a minor gap given the rich schema.

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 100%, so the schema already documents api_key, blueprint, original_values, corrected_values, derivation_rules and formal_constraints. The description's reference to 'the supplied linear rule directions' loosely connects to derivation_rules but adds no syntax, format, or blueprint-vs-inline guidance beyond the schema. Baseline 3 applies.

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 ('measure the numeric difference between original and corrected values') and then decomposes it into named components (projection along rule directions vs residual outside them) plus per-field contributions. The scope is precise enough to distinguish it from siblings like analyze_anomaly or check_drift without opening a 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?

Gives an explicit when-to-use condition ('use with a known-correct version to diff against') and an explicit alternative with its selecting condition ('use analyze_anomaly when you only have the suspicious payload'). It also sets expectations about what the tool will not do (diagnostic only, no causation established, neither record verified).

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