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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It explains the scoring semantics and return fields, which is useful, but it doesn't mention side effects, permissions, rate limits, or whether the operation is read-only. The 'get' prefix implies read-only, but it's not explicitly stated.

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 well-structured: a purpose question, a usage directive, the scoring scale, and the return fields. It's somewhat verbose but front-loaded with the critical 'BEFORE trusting any directional read' warning and uses line breaks for scannability. Every sentence adds meaningful context.

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 no-parameter tool with an output schema, the description is quite complete. It explains the pairwise scoring, the meaning of high/low agreement, names the three sensor verdicts, and elaborates on shift_brewing. It could mention the sensor sources more explicitly, but the output schema presumably covers type details. The action guidance ('trust vs. wait') completes the picture.

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 has zero parameters and the schema coverage is vacuous, so the baseline is 4. The description adds no parameter details (there are none to add), which is appropriate.

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 clearly states the tool's purpose: measuring agreement among three independent sensors. It uses a concrete question ('How much do the three independent sensors agree right now?') and frames it as a pre-flight check before trusting directional reads, which distinguishes it from sibling tools like get_directional_bias or get_regime_current.

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 gives explicit usage context: 'Call this BEFORE trusting any directional read.' It also explains how to interpret results for action (high agreement = act, low agreement = wait). However, it doesn't explicitly name alternatives or say when not to use the tool, so it falls short of a 5.

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