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

With no annotations, the description carries the full burden and does well: it discloses the computation cadence (monthly), the data source (sealed prediction snapshots against observed public outcomes), the reproducibility mechanism (content-sha256 seal), and the honesty policy ('bad numbers are published alongside good ones'). It does not explicitly state read-only behavior, but nothing suggests mutation and the described function is clearly a read-style accessor.

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?

Three sentences, each earning its place: the first defines the resource and contents, the second adds transparency, the third gives a call-to-action use case. The description is front-loaded with the core identity and wastes no 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?

The tool has no required parameters and no output schema, but the description covers what the record contains, how it is computed, how it is sealed, and why to use it. The input schema covers the optional filter and reliability-curve flag. Minor gaps like the exact response envelope are not critical for this low-complexity read tool.

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 both parameters already have adequate inline documentation. The description's mention of 'per-loop calibration scores' slightly reinforces the loop parameter, but it adds no new parameter-specific meaning beyond the schema.

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 identifies a specific resource — the house's verified prediction track record — and enumerates its content (per-loop calibration scores: Brier, ECE, MCE, ROC-AUC, coverage, base rate). It lacks an explicit verb like 'get' or 'list', and does not differentiate from sibling tools such as seal_lookup, but the resource is unambiguous.

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 provides a clear use context: verify the record before buying any paid feed. It does not explicitly contrast this tool with siblings or state when not to use it, but the 'Free: verify the record before buying any paid feed' line gives actionable guidance.

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