memorable_find_neighbors

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

With no annotations at all, the description carries the full burden, and it does disclose the meaningful mechanics: 1024-dimensional vectors and cosine distance, which tells an agent how similarity is computed. It omits result ordering, whether the source memory is excluded from results, and what happens if the memory lacks an embedding, so the disclosure is partial.

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?

A single front-loaded sentence with no filler or redundancy. It is efficient, though its brevity leaves the guidance gaps noted elsewhere rather than using the space productively.

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 two-parameter read tool with a fully documented schema and no output schema, the description covers the core operation and the similarity metric. It still leaves an agent guessing about result ordering, self-inclusion, and failure modes when a memory has no embedding, which matters for a similarity lookup.

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 100%, so both `id` and `limit` are already documented with bounds and a default. The description adds no additional meaning about the parameters, which is acceptable given the schema does the work, but nothing is contributed beyond the baseline.

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?

"Find nearest semantic neighbor memories" gives a specific verb and resource, and the pgvector/cosine clause pins down the retrieval mechanism. It is distinguishable from a query-based search sibling, though it never names that alternative explicitly.

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 offers no when-to-use guidance, no exclusion of alternatives like a text search or context recall, and no stated prerequisite (e.g., that the target memory must already have an embedding). The id-anchored nature of the call is only implied.

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