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

Annotations already indicate read-only and idempotent. The description adds that it returns a full evidence trace (vs collapsed number) and mentions repo scoping behavior. It doesn't contradict annotationsic. Some clarity on the output shape could be added, but with annotations covering safety, this is adequate.

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 concise and front-loaded, but the example 'call introspection_system_probe with {}' is misleading because required parameters exist. The 'Returns' line is somewhat redundant. Still, it's brief and structured fairly well overall.

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 3 parameters and no output schema, the description provides some context (evidence trace, repo scoping, node list source) but lacks details on output structure or how the trace is organized. It's adequate but not complete for a complex tool like this.

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 has no descriptions (0% coverage). The description only mentions that repo is optional and scopes to one repo. It doesn't explain node_id or node_kind meanings beyond referencing confidence's argument shape, which is vague if the agent isn't familiar with that tool. Lacks concrete guidance on parameter values and formats.

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?

Clearly states it returns the full evidence trace for a node, distinguishing from the collapsed number returned by similar tools like introspection_system_confidence. The verb 'Return' and resource 'full evidence trace' are specific, and the mention of 'same argument shape as confidence' helps differentiate from siblings.

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?

Provides guidance on valid node ids (from introspection_system_list_nodes) and optional repo scoping, implying when to use this tool. However, it doesn't explicitly state when to choose this over the confidence tool or other alternatives, though it hints at the distinction between full trace vs collapsed number.

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