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

Annotations already declare read-only and open-world hints, but the description adds crucial behavioral specifics: the BFS is bounded to 15 edges per entity per direction per hop, the response always carries exhaustive: false, and negative results must not be treated as conclusive. This goes beyond the annotations and is highly informative.

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 yet comprehensive, starting with the core purpose, then highlighting the critical bounded limitation with a warning. Uses formatting (bold, emoji) to emphasize key points. Every sentence adds value, with no redundancy or filler.

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 no output schema, the description covers the algorithm, limits, response flag, and usage caveats. It also notes max_depth performance trade-offs. Given the annotations and schema coverage, the description is fully sufficient for an agent to use the tool correctly.

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 input schema already provides full descriptions for all parameters, including max_depth constraints and performance guidance. The description adds little beyond the schema—it mentions the bounded nature but does not clarify parameter syntax or formats further. Baseline 3 is appropriate given complete schema coverage.

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 tool's function: it finds how two entities are connected via a bounded breadth-first search over ownership and control edges in both directions. It distinguishes itself from siblings by specifying the graph traversal algorithm and the bounded nature, which differentiates it from graph_neighbourhood and trace_ownership_path.

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 clear context on when to use it (to find connection paths) and warns about the bounded nature, implying it should not be used for exhaustive connectivity checks. However, it does not explicitly name alternative tools for exhaustive search or when to prefer them.

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