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

Annotations already declare read-only, idempotent, closed-world behavior, so the bar is lower; the description still adds real context by naming the similarity mechanism (EmbeddingGemma 2 vectors) and disclosing what each result carries — shared subjects, places, people, project, or a bare 'wording_only' match. It does not state result ordering, score/threshold behavior, or what happens when a seed record has no near neighbours.

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?

Two dense sentences, with the core similarity behavior front-loaded and the result annotation second. Slightly awkward phrasing ('read most alike') and the parenthetical model name are minor costs, but nothing is padding.

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?

There is no output schema, so the description must carry return semantics, and it does: results describe what each neighbour shares or flag 'wording_only'. Combined with full schema coverage on the three inputs, the definition is close to complete, missing only ordering and empty-result behavior.

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 coverage is 100%, so id formats, the default-5/max-10 limit and the type filter are already documented. The description's type list mirrors the schema enum without adding syntax or edge-case meaning, so baseline 3 applies.

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?

States a concrete retrieval behavior — records whose catalogue descriptions are most alike by EmbeddingGemma 2 vectors — and enumerates the record types searched, so the resource and method are clear. It does not, however, distinguish itself from the sibling find_related or get_semantic_map, which an agent would need to choose between.

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?

There is no explicit when-to-use or when-not-to-use guidance. With a sibling named find_related and other similarity/graph tools (get_semantic_map, get_entity_graph, list_cluster_partners) in the catalogue, the agent gets no criteria for picking this tool over them.

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