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

Beyond the readOnlyHint annotation, the description discloses key behavioral traits: it returns the actual path rather than a boolean, explicitly reports when records are NOT connected, and always notes the limitations of what a shared connection proves. This gives the agent important expectations about output quality and caveats without needing to inspect the schema.

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 well-structured and front-loaded: the core question appears first, followed by the mechanism, then caveats, then input sourcing. While the example is detailed, it earns its place by illustrating the kind of nuance the tool is designed to surface. There is no filler or redundancy.

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 100% schema coverage, a readOnlyHint annotation, and an output schema available, the description covers everything needed to select and invoke the tool correctly. It explains purpose, behavior, input sourcing, non-connection handling, and interpretive limitations, making it self-sufficient for an 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 schema already fully describes both parameters as record IDs, so the baseline is 3. The description adds meaningful value by explaining that these IDs come from archive_search or colour_card and framing them as 'two specific archive records,' which clarifies the exact semantic relationship between the 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 opens with a specific question and clearly defines the tool's function: determining whether two archive records are connected and tracing the exact path between them. It distinguishes itself from a simple yes/no check by stating it returns the actual path, and it differentiates from broad archive tools by focusing on pairwise record relationships.

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 provides clear context for when this tool is appropriate: when checking a specific pair of archive records and wanting the exact reason for a connection. It also gives important interpretive guidance about what a shared connection does not prove. It doesn't explicitly name alternative sibling tools, but it clearly states where to obtain record_id values, which is directly actionable.

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