get_related

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

Adds beyond annotations: explains the vector similarity mechanism and prerequisite for backfill. Annotations already declare readOnlyHint=true, and description does not contradict. No mention of auth or rate limits but fine for a read-only tool.

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?

Three sentences with key information front-loaded: purpose, use cases, and prerequisite. No wasted words.

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?

Output schema exists, so return values need not be described. Tool has only 2 simple parameters. Description covers use cases, prerequisites, and mechanism fully.

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 has 100% coverage with full descriptions for both parameters. Description does not add extra semantics; baseline of 3 is appropriate.

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?

Clear verb ('Find') and resource ('items semantically similar to a given item'), with a specific mechanism ('using vector similarity'). Distinguishes from sibling tools like entity_cooccurrence and find_path by focusing on semantic similarity.

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 explicit use cases ('discovering related concepts, follow-up research, building knowledge clusters') and a clear prerequisite ('Requires embeddings — run backfill_embeddings first if results are empty'). No explicit when-not-to-use listed, but context is sufficient.

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