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

The annotations already indicate readOnlyHint, idempotentHint, and non-destructive, so the core safety profile is known. The description adds meaningful behavioral context: it traverses interest and parent/child edges, returns provenance for each artifact, and specifies the evidence chain (D8 seeds-walked). It also discloses the return shape (evidenced vs no_evidence_available). No contradiction with annotations.

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 somewhat redundant: it repeats the return type and includes an example call that adds little value. The core content is front-loaded with the purpose, and the parameter explanations are adequate, but the example and the final 'Returns' sentence are redundant and could be trimmed.

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 the tool's complexity (traversal over graph edges, multiple parameters, evidence chain), the description provides a thorough overview without needing an output schema. It covers purpose, parameters, defaults, traversal behavior, and return types. It doesn't specify edge cases like empty result or unreachable nodes, but the evidence-chain disclosure compensates. Overall, it's nearly complete.

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 has 0% coverage, meaning the description must explain the parameters. It does explain origin_slug (CO directory slug, example), max_hops (default 1, bounds depth), and include_parent_child (default true, meaning). However, it doesn't detail max_hops' allowed range or include_parent_child's exact effect on the return beyond 'counts as reach', which leaves room for slight enhancement.

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 it returns the REACH of a change, specifying every artifact across every registered repo that declares interest, with traversal over the change-graph's edges. It distinguishes itself from other introspection tools by focusing on the reach (impact) rather than the change itself, and provides a concrete example target.

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 explains how traversal works (max_hops bounds depth, include_parent_child toggles the decomposition tree) and implies when to use it (to find all surfaces a change reaches). It doesn't explicitly list alternatives or when-not-to-use, but the context signals (sibling tools) provide enough distinction.

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