dt3_related

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

The description adds meaningful behavioral detail beyond the annotations: results are permission-filtered, suggestions are advisory, and duplicate detection follows DEVONthink's logic rather than a fresh disk hash. This complements the readOnly and idempotent hints without contradicting them.

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, with three focused sentences: one for purpose, one for permission filtering, and one for behavioral caveats. It is well-structured with no redundant or vague content.

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 output schema is available, the description does not need to explain return values. It provides enough context about the kinds of related items and key behavioral caveats to enable correct usage, though it could have included a brief example or parameter-relationship mapping for extra clarity.

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 uuid parameter is well described (accepts UUID or x-devonthink-item:// link, and notes ignored parameters), and the kind enum values are self-explanatory. However, limit and offset lack descriptions, and the relationship kinds are not further elaborated. Since schema coverage is only 25%, the description only partially compensates for the missing parameter detail.

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 identifies the tool's purpose with a specific verb ('Find') and a distinct resource scope: native similar documents, classification suggestions, duplicate files, and incoming/outgoing references. This makes it readily distinguishable from sibling tools like search or list operations.

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 the tool by specifying the types of relationships it retrieves (similar, classify, duplicates, incoming, outgoing) and includes useful caveats about permission filtering and the advisory nature of suggestions. It stops short of explicitly contrasting with sibling tools, but the scope is clear enough for practical selection.

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