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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's real contribution is the ranking semantics: distance is cosine over behavior_vec and lower means more alike. That directionality is genuinely useful and non-obvious, though return shape and result-size behavior are left unstated.

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 core definition is front-loaded in one dense, useful sentence, followed by a use case. The closing implementation trivia ("HNSW vector index, db.idx.vector.queryNodes") adds little for a caller and is the only sentence that does not fully earn its place.

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?

With no output schema, the description should pin down the return shape more than "with their banks"; k is undocumented and there is no mention of ordering guarantees or result limits. It is adequate to call the tool but leaves the agent guessing about output size and fields.

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 0%, so the description carries the full burden for two parameters. It says nothing about account_id or, more importantly, k (the result count, default 5) – an agent cannot tell from any source how many neighbors it will get back.

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 names a concrete operation: ranking accounts by cosine distance over Account.behavior_vec and returning them with their banks. It is specific about the mechanism and result, though it never explicitly contrasts itself with structural siblings like account_network or connected_components, which is what a 5 would require.

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?

"Useful to find mule accounts that act like a known one at other banks" gives a clear investigative context for when to reach for it. It stops short of naming alternatives or stating when-not to use it (e.g., for structural rather than behavioral similarity).

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