projection_calibration

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

The description explicitly states the tool 'Stores the measured weight (used by every projection)', i.e. it persists state, while the annotations declare readOnlyHint=true. That is a direct conflict between described write behavior and the read-only annotation, so the behavioral signal is actively misleading.

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?

Two sentences, front-loaded with the primary action and outputs before the storage/override detail. The second sentence is dense but each clause (storage trigger, override precedence) carries distinct information, so little is wasted.

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 usefully names what is returned (per-stat RMSE, normalized error, best blend weight) and explains the storage trigger and config override. It is reasonably complete for a no-argument analysis tool, apart from the annotation conflict.

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?

The tool takes zero parameters and the empty input schema leaves nothing to document, so the baseline of 4 applies. No parameter meaning is required or missing.

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+resource (grades logged forecasts) and enumerates concrete outputs: per-stat RMSE, normalized error for engine-only/ESPN-only/blend, and the best blend weight. The scope is unambiguous, though it never differentiates itself from near-neighbor siblings like prediction_calibration or signal_grades.

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?

It implies usage context (grade forecasts against the next 14 days of box scores; a weight is stored once enough forecast dates are graded), which hints at a prerequisite. However, it gives no explicit when-to-use or when-not-to-use guidance and never points to the alternative calibration/grade siblings.

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