record_calibration_correction

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

With no annotations, the description carries the full burden. It does disclose the Kiln Pro entitlement requirement, which is real behavioral context, but says nothing about side effects: whether the correction alters the calibration profile, how confidence_adjustment is applied, or whether the event is reversible/auditable.

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?

Only the first sentence does tool-description work; the remaining three sentences are a Kiln Pro upsell and a pricing URL. Roughly half the text is marketing rather than invocation guidance, which is not concise for an agent-facing definition.

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?

A five-parameter mutation tool with no annotations and no output schema needs more: what the call returns, whether the linked observations must already exist, and what effect the correction has on subsequent calibration queries. The description covers purpose and entitlement only.

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 80%, so the schema already documents all five parameters including defaults. 'Linking two observations' loosely maps to original_observation_id and corrected_by_observation_id but adds no semantics about what 'reason', 'annotation', or 'confidence_adjustment' mean in practice. Baseline 3.

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 states a specific verb and resource ('Record an explicit correction event') and adds the key relational detail that it links two observations. It doesn't differentiate from near-siblings like apply_calibration_recommendations, revert_calibration_recommendations, or ingest_measurement, and 'correction event' is left undefined.

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?

No guidance on when a correction should be recorded versus using ingest_measurement or apply_calibration_recommendations, and no statement of prerequisites beyond the paywall note. The one usable signal — 'Requires Kiln Pro' — is a licensing gate, not usage guidance.

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