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

Annotations already declare readOnly/openWorld/idempotent, but the description adds substantial behavioral context: the two distinct execution paths, the return verdicts with citations, and the critical nuance that 'could_not_verify' means no check happened and carries a verification_error, distinguishing it from 'unsupported'. This goes beyond the annotations to explain error handling and caveats, with no contradiction.

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 fairly long but information-dense, with clear structure: trigger phrases, usage rule, path breakdown, return value, and an IMPORTANT caller note. Every sentence contributes, though the opening examples could be trimmed without losing much. It earns a 4 for being organized and useful despite verbosity.

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?

Without an output schema, the description fully specifies the return shape: verdicts, actual values, citation, and reasoning. It also covers both claim types, the tolerance override, and error semantics. For a tool with two parameters and complex routing, this description gives the agent everything needed to select and invoke correctly.

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 already fully describes both parameters (claim and tolerance_pct) with examples and constraints, so schema coverage is 100%. The description repeats the tolerance advice but does not add meaning beyond the schema; it mainly reinforces the schema's details. Baseline 3 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 identifies the tool as natural-language claim verification against authoritative sources, with a specific verb ('verify', 'fact check') and resource ('authoritative sources'). It distinguishes from sibling tools by explicitly scoping to factual claim checking and even mentions it replaces sequential pipeline calls.

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 states explicitly: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also differentiates between two paths (SEC EDGAR for company-financial claims vs grounded pipeline for all others), giving clear when-to-use context. Additionally, it advises on interpreting 'could_not_verify' versus 'unsupported', which guides callers on when to rely on the result.

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