llm_dag_propose

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

Even with readOnlyHint=true, the description goes well beyond annotations by stating that outputs are hypotheses to validate, not statistical identification, and that human review or data-driven falsification is required. It also discloses instability and hallucination failure modes with concrete fixes, which is valuable behavioral context far beyond the structured hints.

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 information-dense but well organized with labeled sections (Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N). Every sentence adds distinct value—no filler—and the core purpose is front-loaded in the first sentence.

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 tool with 10 parameters and a rich output schema, the description covers the conceptual framing, prerequisites, failure modes, mitigations, alternatives, and even a minimum-N heuristic. The output schema handles return-value details, so nothing essential is missing for an agent to call this tool 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?

Schema description coverage is 100%, and each parameter already has a detailed description in the schema. The tool description reinforces that `variables` and `domain` are the core inputs, but adds no new parameter-level semantics beyond what the schema 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 opening sentence states a specific verb ('propose'), a concrete resource ('candidate DAG'), and the inputs ('variable names + domain description'). It also explicitly names sibling alternatives later, so an agent can distinguish this from sp.dag, sp.causal_discovery, and sp.llm_dag_constrained without opening their schemas.

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 clear pre-conditions (domain context, bounded variables, configured/logged LLM provider), failure modes, and a list of alternative tools. However, it does not explicitly state when to choose one alternative over another (e.g., 'use sp.llm_dag_constrained when you already have structural constraints'), so the routing guidance is helpful but not fully explicit.

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