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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, so the safety profile is covered. The description adds beyond annotations: it explicitly states 'Never silently reconciles drift,' describes the two possible return kinds ({kind: "evidenced", value, chain} or {kind: "no_evidence_available", reason}), and mentions provenance (comai-plan CO 013-003 / federation CO 006). This is valuable context beyond the structured 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 dense but well-structured. It front-loads the main purpose, then details graph components, drift behavior, return contract, provenance, and an example call. Every sentence adds value, though the provenance line and example could be considered non-essential. Slightly verbose but not wasteful.

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 moderate complexity (graph with nodes/edges, drift reports, multiple return kinds), the description is complete. It explains the graph structure, the meaning of drift, the return schema (evidenced/no_evidence), and even provides an example invocation. With no output schema available, the description fully carries the burden of explaining the result shape, and it does so effectively.

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 tool takes zero parameters, so the schema provides full coverage (100% trivial). The description does not need to explain parameters, and it doesn't. Baseline for 0 parameters is 4, which is appropriate; nothing to add.

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 the verb (Return), the resource (dependency graph of change orders), and the scope (across every registered ComOS repo). It then itemizes the graph components (nodes, parent/child edges, interest edges, drift reports) distinguishing it from sibling introspection tools like introspection_system_list_nodes or introspection_system_diff.

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 implies when to use this tool—whenever you need the full dependency graph of change orders, especially to inspect drift without silent reconciliation—but does not explicitly name alternatives or state when NOT to use it. The 'Never silently reconciles drift' behavior hints at a use case but no direct comparison to other introspection tools.

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