Get Research Prompts

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals that the tool produces one bounded, scope-isolated prompt pair per remaining scope, imposes a strict agent-isolation constraint, and requires downstream validation and registry building. This goes well beyond a generic 'get prompts' statement and tells the agent what to expect and what to do next.

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 two purposeful sentences: the first states the deliverable, the second specifies the exact workflow and constraints. There is no filler or repetition of schema fields, and the most important behavior is front-loaded.

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?

For a single-parameter tool with an output schema, the description covers the input, the generated artifact, the operational constraints, and the next step in the pipeline. Nothing essential is missing for an agent to invoke and follow through correctly.

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 only declares `run_dir` as a string with no description and 0% schema coverage, so the description must compensate. It does by explicitly referencing `<run_dir>/request.yaml`, which tells the agent that `run_dir` is the path to the run directory containing the request file. It adds the key semantic meaning the schema lacks.

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 ('renders') and a concrete resource ('researcher and reviewer prompts for a run's research request') tied to `<run_dir>/request.yaml`. It clearly differentiates this from siblings like build_research_consensus or validate_evidence_review by framing it as a prompt-generation step, not an analysis or validation step.

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 usage context: run one prompt per remaining scope with a separate agent, write YAML artifacts, validate them, then call build_session_registry. It also includes an explicit exclusion ('never let one agent research two scopes or review its own research'). It does not name alternative tools for comparison, but the procedural guidance is strong enough to direct correct use.

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