verify_claims

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

There are no annotations provided, so the description carries the full burden of behavioral disclosure. It explains what the tool does not do (no source discovery, no live retrieval, no absolute truth claim), defines 'verified' operationally, and mandates human review. These non-obvious caveats are exactly the kind of context agents need.

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 compact, front-loaded with what the tool does, and every sentence adds value: verdict vocabulary, evaluation dimensions, limitations, and operational caveats. No repetition or filler.

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 a single nested request parameter and no output schema, the description covers the output vocabulary, the input concepts, the judgment criteria, and the key caveats. The one clear gap is that the exact nested contract is deferred to get_schema rather than described in the tool text, but that is a reasonable trade-off for such a nested structure.

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 schema describes the top-level wrapper and points to get_schema for details, so the baseline is 3. The description adds meaningful conceptual semantics by mapping the evaluation dimensions (freshness, source class, source groups, conflicts, jurisdiction, subject identifiers, as-of date) to what the claims and evidence parameters should contain.

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 operation ('Issue a bounded factual Claim Verdict'), the resource ('caller-supplied evidence records'), and the specific output verdicts. It distinguishes itself from sibling tools by explicitly fencing off source discovery and live retrieval, making the niche unmistakable.

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 gives strong contextual signals for usage: use it when evidence is already supplied and a bounded evidentiary verdict is needed. It also provides explicit when-not clauses ('No source discovery or live retrieval', 'not absolute truth', 'Human review remains required'). It does not name specific sibling alternatives, so it stops short of full routing guidance.

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