HAKEM Single-Agent Review

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

Despite no annotations, the description discloses that the server wraps the prompt in <manuscript> tags, prepends RAG examples when agentType is supplied, runs the Claude model, consumes Science AI Journal credits, and returns a detailed structured output. This gives the agent a clear understanding of 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?

The description is dense but not overly long; it contains no fluff. However, it could be slightly restructured for easier scanning, e.g., by separating output fields into a list. Still, every sentence earns its place.

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 covers the output fields and server behavior well, given the tool's complexity and lack of output schema. It might benefit from mentioning authentication requirements or potential error conditions, but it is sufficiently complete for correct agent invocation.

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 100% with descriptions for both parameters. The description adds valuable context: it specifies that the prompt should include manuscript text plus agent-specific framing, explains the server-side handling, and clarifies the meaning of agentType and its default behavior.

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 that the tool runs a HAKEM specialist agent on a prepared prompt and returns a structured editorial decision with specific fields. It names the five agent types and explicitly contrasts with the full 5-agent flow available on the web UI, distinguishing it from sibling tools.

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 explains that this tool is for single-agent review and directs users to the web UI for the full multi-agent flow, providing a clear alternative. However, it does not outline when to use this tool versus other siblings like pre_check_paper, but the context is sufficient.

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