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

Annotations already declare read-only, idempotent, and non-destructive. The description adds important behavioral nuance: the crucial difference between could_not_verify (check did not happen, not evidence) and unsupported (no source exists), plus the internal routing and error handling. This is valuable context beyond annotations, though it doesn't fully disclose every pipeline detail. No contradiction with annotations.

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 relatively long but well-structured: it opens with query examples, then states usage, routing, return types, and a critical caller note. Every sentence carries useful information and there is no wasted wording, though it could be slightly trimmed for a tighter presentation.

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 that there is no output schema, the description carries the burden of explaining return values. It lists the verdict types, explains the error semantics of could_not_verify, and mentions citations and reasoning. It also describes the two processing paths. This is sufficient for an agent to invoke and interpret results, though a fuller definition of each verdict would improve completeness.

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 coverage is 100%, and both parameters already have detailed descriptions including examples for claim and full explanation of tolerance_pct with defaults and use cases. The tool description does not add additional parameter-specific meaning beyond what the schema provides, so it meets the baseline of 3 but does not exceed it.

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 a natural-language claim verification service with verbs like 'fact check' and 'verify the claim that…'. It distinguishes itself from siblings by focusing on returning a verdict with citations, not open-ended research, and explicitly names the two processing paths (financial vs. general). This leaves no ambiguity about what the tool does.

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 explicitly states when to use: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also provides context by distinguishing company-financial claims (SEC EDGAR path) from other claims, and notes it replaces multiple sequential calls. It does not explicitly say when not to use or name alternatives like deep_research, but the usage context is clear.

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