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

The description directly contradicts the openWorldHint=false annotation. The annotation indicates a closed-world assumption, meaning 'no result' is definitive, but the description says 'NO_MATCH means no observed path within budget, not that they are unconnected,' which is an open-world caveat. This inconsistency could mislead the agent about the certainty of negative results, making the tool's behavior unclear.

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 and well-structured: three sentences that front-load the core purpose, then provide hop-level details, and conclude with result interpretation. Each sentence adds distinct value without redundancy. There is no filler, and the most important information (purpose and scope) appears first.

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 graph-path tool with no output schema, the description covers the essential behavioral aspects: hop types, search direction, depth limit, and the meaning of NO_MATCH. However, it does not specify the exact return structure (e.g., ordered list of nodes/edges, whether multiple paths are returned, how sources are attributed). The absence of an output schema means the description should include more detail about the response format, but the given information is largely sufficient for basic invocation.

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 already provides detailed descriptions for from_dfx_id and to_dfx_id (covering the DFX graph types), and max_hops has default/min/max constraints. The description adds minimal meaning by clarifying that max_hops is the search depth ('Bidirectional search up to max_hops') and reiterating the default value, but it does not substantially enhance understanding of the parameters beyond the schema. With 67% schema coverage, the description partially compensates but not fully.

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 purpose: finding an evidence-backed path between two DFX IDs across all graphs. It specifies the hop types (published relationships with sources, SAME_AS identity links) and mentions the bidirectional search, which distinguishes it from siblings like search_relationships (which likely returns relationships for a single entity) and get_capital_paths (which focuses on capital flows). The verb and resource are specific and the scope is unambiguous.

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 the use case (finding connectivity between two known DFX IDs) and provides interpretation guidance for the NO_MATCH result. However, it does not explicitly mention alternatives or conditions for choosing this tool over siblings, nor does it state when not to use it. There is no exclusion or comparison with tools like search_relationships or verify, leaving the agent to infer when this tool is appropriate.

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