Retrieve with context

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

The description reveals behaviors beyond annotations (readOnlyHint, openWorldHint): it explains the one-hop expansion logic, default parameter behaviors, the dropping of the embedding column, and the requirement for the vector extension. This is thorough and adds significant value.

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 with a clear summary, but it is somewhat lengthy. Every sentence adds value, though minor pruning could improve conciseness.

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 complex tool with 10 parameters and a rich output schema, the description covers the algorithm, parameter behaviors, limitations, dependency, and return structure. It provides an example and is sufficient for an agent to use the tool correctly.

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?

With only 10% schema description coverage, the description compensates well by explaining key parameters (query_vector, include_parents, include_children, max_related) and their defaults. It also provides an example. However, it does not explain optional parameters like metric or the meaning of k in 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 states its function as 'Context-packed k-NN retrieval (a one-shot RAG building block)' that runs vector search and expands results one hop along foreign keys. This distinguishes it from sibling tools like vector_search which likely perform plain vector search without context expansion.

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 frames usage as a RAG building block and lists limitations ('1 hop only', 'inbound expansion same-schema only'), helping an agent decide when to use it. However, it does not explicitly name alternative tools or state when not to use it, leaving some ambiguity.

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