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

Annotations already declare readOnlyHint and destructiveHint. The description adds significant behavioral context: data is computed from each venue's OWN probability ~24h before resolution, over resolved markets with >=24h history, and venues below minSample appear in pending. This goes beyond the annotations by explaining the methodology and data freshness constraints. No contradictions.

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?

The description is front-loaded with the purpose and key metrics. Every sentence adds value, explaining data source, conditions for pending, and how to use. Slightly verbose in detailing the reliability curve but remains focused. No wasted words.

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?

Given no parameters and an existing output schema, the description covers all necessary context: what data is returned, how it is computed, when data is pending, and a usage example. It leaves no ambiguity for the agent.

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 input schema has no parameters (schema coverage 100%), so the description cannot add parameter-level meaning. The description effectively documents what the tool returns (calibrationError, sampleSize, etc.) and has an output schema defined. Baseline 4 is appropriate since no parameters exist to elaborate on.

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 description opens with 'Free public per-venue forecast-accuracy scorecard', clearly stating the tool's purpose. It specifies the exact metrics provided (calibrationError, sampleSize, meanWinnerConfidence, reliability curve) and explicitly distinguishes itself from other tools by focusing on venue-level calibration. This effectively answers 'what does this tool do?' and differentiates from siblings like pm_data_canonical or pm_data_overview.

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?

The description explicitly states the use case: 'Use this to answer \'which venue forecasts best\' with evidence, not vibes'. It also explains when data is pending due to low sample size. While it doesn't explicitly list alternatives or when not to use, the sibling tools are numerous and the description's clear focus on venue calibration guides appropriate usage.

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