screen_for_rwe_signals

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 candidly discloses the tool's experimental status, lack of ground-truth oracle, false-positive problem, and the tendency for results to be dominated by unrelated uses of 'registry.' It also clarifies the output's role as a candidate list, not a finding. This is exemplary transparency beyond any structured data.

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 well-structured and front-loaded with a clear 'EXPERIMENTAL' warning. Every sentence adds critical information: what it does, how it aggregates results, and the crucial limitations. It is appropriately sized for the tool's complexity and caveats, with no wasted words.

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?

The description fully contextualizes the tool's purpose, methodology, and limitations. An output schema is present, so explaining return values is not necessary. The description covers the behavioral caveats and the candidate-list nature, making it complete for an experimental screening tool.

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 both parameters (extra_terms and limit_per_term) with descriptions, providing 100% coverage. The description itself does not add parameter-specific semantics beyond what the schema already provides, so the baseline of 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 states a specific verb and resource: 'Sweep drug labels for registry / real-world-evidence signals.' It clearly distinguishes this from sibling tools like search_drug_label by focusing on the sweep-and-aggregate behavior across the label corpus, rather than a general search.

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 provides strong usage guidance: it is experimental, unvalidated, and has a known false-positive problem. It explicitly warns that output is a candidate list for human review, not a finding or reportable count. However, it does not explicitly name alternative tools or state when to prefer them over this tool, so it loses a point.

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