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

Annotations already declare read-only and non-destructive behavior. The description adds substantial behavioral context beyond this: accepted pf.* namespace, frozen registry certificate, construct_id being fully resolved, problem_id depending on a future join table, and condition_id gated on HO-761. This gives the agent realistic expectations about current functionality.

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 sentences with the purpose front-loaded and caveats packed into the second sentence. It is appropriately sized, though opaque ticket references like MF-711, HO-761, and the certificate hash add jargon that may not be actionable for an agent.

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 output schema covers return shape and annotations cover safety, but the description does not clarify whether problem_id, construct_id, and condition_id are mutually exclusive or combinable, nor does it explain what the limit parameters precisely affect. For a tool with five optional parameters and partial delivery dependencies, this leaves some ambiguity about the exact invocation contract.

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?

With schema description coverage at 0%, the description must compensate for the schema's silence. It explains problem_id, construct_id, and condition_id semantics and availability, but it does not describe limit_priors or limit_interventions, which are only inferable from their names and min/max constraints. The ID format guidance is also partial beyond pf.*.

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 opens with a specific verb and resource: 'Retrieve the full causal chain from a construct, condition, or problem to interventions, with evidence grades at each hop.' This clearly defines what the tool does and differentiates it from lookup/search siblings that do not promise chain tracing.

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 context for when the tool is relevant and includes important availability caveats (condition_id gated, problem_id pending MF-711). However, it does not explicitly name alternatives or state when to prefer this tool over siblings like principia.evidence.for or the various lookup/search tools, leaving routing partly implicit.

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