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

No annotations are present, so the description carries full burden. It compensates well by disclosing the corpus-first behavior, live sources (HackerNews, StackExchange, Lemmy), determinism, return components (cited voices, sample size, live_scan tier, ClaimReview), and 24-hour caching. It does not cover failure or empty-result edge cases, but the core behavioral expectations are clear.

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 three sentences with the key differentiator front-loaded and no filler. Every sentence adds meaningful information about scope, behavior, return shape, or usage 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?

Given there are no annotations and no output schema, the description is notably complete: it covers inputs, branch logic, live sources, return fields, caching, and when to invoke it. It does not document error cases or exact output JSON, but an agent has enough to call it 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?

Schema coverage is 0%, so the description must compensate for bare parameter names. It clarifies that 'product' can be any product, reviewed or not, and 'claim' is the statement to verify, but it does not explain acceptable formats, lengths, or examples. This is partial compensation, not full.

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?

Opens with a specific verb and scope ('Verify a claim about ANY product') and clearly distinguishes itself from verify_claim by covering both reviewed and unreviewed products with a corpus-first/live-scan fallback. The two-branch behavior ('if GYIBB publishes a review... Otherwise...') makes the tool's unique role immediately obvious.

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?

Explicitly states when to use this tool: 'Use when verify_claim says no_data, or when you need a fresh read on a product outside GYIBB's catalog.' It also names the alternative behavior and the fallback ordering, giving an agent a clear decision rule among siblings.

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