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

Since no annotations are provided, the description must carry the full behavioral burden. It discloses the deterministic nature (pass/needs_qualifier/block), the reason code for block, and the provision of a safe sentence and required attribution. It also hints at the underlying logic ('most misuse is omission'). However, it does not mention error handling for invalid IDs or the exact output schema, which is a minor gap. It is still quite transparent for a read-only check tool.

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 dense but well-structured, leading with a strong imperative ('USE BEFORE...') that front-loads the most critical information. It then explains the function, adds a helpful note about common misuse, and ends with an exclusion. While a bit lengthy, every sentence adds value and the flow is logical. It could be tightened but is not bloated.

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 the tool has 8 parameters, no schema descriptions, and no output schema, the description is incomplete. It fails to define each boolean parameter's meaning and how they relate to the listed use cases. The output structure is only partially described (verdict types) but not the format of the safe sentence or attribution. The agent would need additional context to correctly construct the invocation, especially for parameters like qualifier_dropped and attribution_present.

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 0%, so the description must compensate by explaining the parameters. It mentions 'claim id' and 'population, period, scope, cause, individual prediction, recommendation, legal conclusion,' but does not map these to the actual schema parameters (passport_id, causal_assertion, legal_conclusion, qualifier_dropped, attribution_present, individual_prediction, scope_beyond_universe, personalized_recommendation). The booleans are not explained, leaving the agent guessing how to set them. This is a significant deficiency given zero schema help.

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: to vet claims involving FRC figures before writing them, returning a verdict and safe sentence. It specifies the resource (FRC figures) and the action (check claim contract), and distinguishes from siblings by explicitly excluding non-FRC figures. The verb 'check' and the detailed scope make it 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?

Provides an explicit 'USE BEFORE WRITING ANY SENTENCE CONTAINING AN FRC FIGURE' directive, which is a strong when-to-use condition. It also gives a clear exclusion: 'NOT FOR: figures published by anyone other than FinanceRateCalc.' It even explains the common misuse pattern, guiding the agent on when to invoke this tool. Alternatives are not named, but the exclusion effectively routes away from non-FRC sources.

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