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

While annotations already state readOnly and idempotent, the description adds crucial behavioral detail: 'Never silently reconciles drift' and the exact return envelope for evidence or absence. This goes beyond annotation to explain how the tool behaves, making it transparent.

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 front-loaded with the core purpose and then expands into details. It's somewhat long but each sentence adds meaning; no redundancy. The example call is helpful.

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?

With no output schema, the description fully specifies the return shape and examples. It also includes provenance and key behavioral caveat, making it self-contained for the agent.

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 has zero parameters)Skip. Per rubric, baseline is 4 for 0 params. The description correctly confirms it takes no arguments and provides return structure, so it doesn't need to explain parameters.

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 explicitly states it returns the dependency graph of change orders across all repos, detailing nodes, edges, interest edges, and drift reports. It clearly differentiates from siblings like introspection_system_change_reach by focusing on the full graph structure rather than reachability or other aspects.

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 what the tool does but not when to use it versus alternatives like introspection_system_change_reach or introspection_system_diff. It lacks explicit exclusions or guidance on selecting this tool, though the purpose is clear.

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