Compare two studies and explain why they disagree

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

With no annotations provided, the description carries the full burden of disclosure. It is exceptionally transparent: it lists exactly what is extracted (species, model, intervention, etc.), states that values are verified against source text with deterministic grounding, explains the output structure (unranked differences and ruled-out identical dimensions), commits to verbatim quotes and 'not reported' for unsupported fields, and clearly states it 'Never picks a winner.' This goes far beyond a typical description and leaves no ambiguity about the tool's behavior.

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?

Despite being a long paragraph, every sentence contributes unique information: purpose, extraction details, verification, output structure, limitation handling, and dependency. The critical scoping statement ('Never picks a winner.') is placed near the end but is memorable. There is no redundancy or filler; the density is appropriate for the tool's complexity.

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 complexity of comparing two studies and the absence of an output schema, the description is remarkably complete. It covers input requirements, the exact dimensions extracted, the verification process, the output format (unranked differences, ruled-out identicals), and the requirement for an API key. An agent can confidently invoke this tool correctly without needing additional context from elsewhere.

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 covers 100% of parameters, so the baseline is 3. The description adds value by explaining the id/text alternatives for each paper ('Each paper is given as {id} (PMID or DOI) or {text}') and highlighting the need for a citation when supplying raw text. This goes beyond the schema's field descriptions, providing context that helps the agent choose the correct input form.

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 opens with a specific verb and resource: 'Explain WHY two scientific papers reach different conclusions.' It clearly defines the tool's core function as comparative explanation, and distinguishes it from siblings by noting the no-key alternative (compare_example). The purpose is unambiguous and not a tautology of the tool name.

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 explicitly states when to use the tool (requires ANTHROPIC_API_KEY) and provides a clear alternative for the no-key case: 'use compare_example for a no-key demonstration.' It also implies the input format (PMID/DOI or text), giving practical guidance on how to supply the two papers. This is sufficient and distinct.

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