OpenEvidence Ask

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

With no annotations, the description fully bears the burden. It discloses the fire-and-forget return (immediate pending), blocking with wait_for_completion, reliance on relay extension, and deprecation of direct POST. No contradictions.

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 a single paragraph front-loaded with core behavior and key distinctions. It is dense and efficient, though slightly structured as a block of text. Every sentence adds value.

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?

Despite good coverage of core behavior and two key parameters, with 13 parameters and no output schema, the description omits details on many parameters (e.g., timeout_sec, article_type, include_bibtex) and the full output structure. It is adequate but not fully complete given complexity.

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 description coverage is only 8% (only original_article_id described). The description adds meaning for wait_for_completion and original_article_id, but covers few of the 13 parameters. Many defaults are listed but not explained in context, so it partially compensates.

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 states it creates a question, distinguishes fire-and-forget vs. blocking modes, and explicitly differentiates from oe_article_get for fetching results. It also mentions follow-up usage via original_article_id, providing a specific verb and resource.

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 explicit guidance: when to use fire-and-forget (default) vs. wait_for_completion, how to do follow-ups, and the requirement of a connected relay extension. It implies context (browser tab free for other sessions) and notes deprecation of a direct method.

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