step_research

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

With no annotations, the description carries the full burden and does well: it discloses that discovery, collection, and indexing are executed, that the run pauses in 'awaiting_extraction', and that verification is gated until all claims reach a terminal disposition. It omits idempotency, error behavior, and permissions, keeping it short of a 5.

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?

Three compact sentences, front-loaded with the core action followed by the state transitions. Every sentence carries meaning; no 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?

An output schema exists, so return values need not be explained. For a complex state-machine tool the state coverage is strong, though the absence of any note on idempotency or repeated invocation leaves a minor gap.

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 0% and the single parameter run_id is never explained in the description. The parameter name is fairly self-evident, so the gap is modest, but the description does nothing to compensate for the missing schema documentation.

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?

States a specific verb ('Advance') and resource ('the research workflow for a run'), and frames the tool as a state-machine driver. An agent can distinguish it from siblings like get_research_state or verify_claims, though it doesn't name them explicitly.

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?

Gives clear state-conditional guidance: it explains what the tool executes depending on whether the run is in 'brief_compiled'/'expanding', 'awaiting_extraction', or 'awaiting_verification'. No explicit alternatives are named, but the branching conditions effectively tell the agent when to invoke it.

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