Relate records

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds the specific algorithm (Jaccard) and scope (rest of index), which is useful but does not contradict annotations. It does not fully describe behavior such as output format or sorting.

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 a single concise sentence with no unnecessary words. It effectively communicates the core functionality without repetition or excess.

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 tool's simplicity (2 params, no output schema, safe annotations), the description is largely sufficient. However, it could be more complete by indicating the output format (e.g., list of records with similarity scores sorted descending). Still, it provides the essential context for an AI 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?

Schema description coverage is 50% (only 'id' has a description). The description does not mention the 'limit' parameter or its default/range. It provides no additional meaning beyond the schema for 'id', and fails to compensate for the undocumented 'limit' parameter.

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 computes Jaccard keyword similarity between a given record and all others in the index. It uses specific verbs and resources (compute similarity, record, index), distinguishing it from siblings like gkb_query or gkb_read_kb_content.

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?

No explicit guidance on when to use this tool versus alternatives. The description implies usage for finding similar records, but does not mention prerequisites, when not to use, or how it differs from other similarity-related tools among siblings.

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