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

Annotations already declare read-only and idempotent behavior, and the description adds that the response carries node-specific evidence rather than a collapsed number, clarifying the output format. No contradiction with annotations, and given the read-only nature, side effects are not a concern.

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 succinct, containing a clear purpose, an explanation of the difference from confidence, and an example invocation. No unnecessary words or redundant details.

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 includes an example call, references to related tools for argument sourcing, and specifies the return content, providing enough context for an agent to invoke the tool correctly. The mention of 'Phase A' also sets expectations about scope.

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 schema defines node_kind, node_id, and optional repo. The description adds meaning by stating that repo scopes to one repo and that valid node ids come from a list function, but it does not individually elaborate on node_kind values, relying instead on the enum and the 'same argument shape as confidence' note.

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 returns the full evidence trace for a single federation node, and distinguishes it from confidence by contrasting 'full evidence trace' with a 'collapsed number'. It also notes the argument shape similarity, giving a precise purpose.

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?

It provides usage context by pointing to introspection_system_list_nodes for valid node ids and explains that the optional repo scopes to one repo (Phase A). However, it does not explicitly list alternatives or when to avoid this tool, though the implication of a detailed counterpart to confidence is present.

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