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

Annotations already declare the tool as read-only (readOnlyHint=true) and non-destructive (destructiveHint=false), so the description doesn't need to restate that. It adds that the response carries 'node-specific evidence rather than a collapsed number' and that valid node ids come from another tool. However, it doesn't describe the structure of the evidence trace or any error behavior, missing an opportunity to enrich beyond what annotations provide.

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 somewhat verbose with an unhelpful example ('call introspection_system_probe with arguments {}') that implies no required parameters, contradicting the schema. The phrase 'Returns: The probe result for the requested target' is redundant and adds little. Could be tightened to focus on the evidence trace and required parameters.

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?

Given no output schemabool, the description should clarify what the 'evidence trace' looks like or at least mention that it differs from a scalar confidence value. It references introspection_system_list_nodes for valid ids, which is helpful, but lacks details on node_kind values, error conditions, and the overall behavior for different node types. The misleading example further reduces completeness.

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 coverage is 0% (description only references 'repo' and the argument shape relative to 'confidence'). The required parameters node_kind and node_id are not described beyond the example call, which is incorrect (empty {} ). The mention of 'repo' being optional adds some value, but the enum values for node_kind are left to the schema without explanation.

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 action ('Return the full evidence trace') with a clear resource ('a single federation node'). It hints at differentiation from the 'collapsed number' tool (likely confidence) but does not explicitly name or contrast with the sibling introspection_system_confidence. The reference to 'same argument shape as confidence' provides context but could be clearer about the distinguishing 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?

Provides some usage guidance: mentions that valid node ids come from introspection_system_list_nodes Light, and that `repo` optionally scopes to a single repo. However, it does not explicitly state when to use this tool over alternatives (like confidence or list_nodes), nor does it mention the requirement for node_kind and node_id as mandatory parameters beyond the example with empty arguments, which is misleading.

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