semantic_recall

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds real value beyond them by disclosing the retrieval mechanism (vector search, server-side autoEmbed) and scope (all six layers), which explains result behavior. It does not describe ranking or result shape, but annotations and the limit param carry much of that burden.

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 tight sentences, front-loaded with the core purpose and mechanism, with no filler. The final sentence routing to keyword-based siblings is efficiently placed at the end, though the phrasing could be marginally tighter.

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 read-only search tool with full annotation coverage, a fully documented schema, and no output schema, the description supplies enough: what it does, how it differs from keyword search, and the embedding mechanism. Return format and pagination with limit are not covered, but that is a minor gap given the structured data available.

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 baseline is 3. The description reinforces that search spans all six layers, implicitly mapping to the layer enum's default, but adds no syntax or format detail beyond the schema's own per-parameter descriptions (including the voyage-4 embedding note).

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 specific verb (semantic search) and resource (memories across six layers), and names the mechanism (Atlas Vector Search autoEmbed) plus the distinguishing property (finds conceptually related memories without keyword overlap). It explicitly contrasts itself with the keyword-based siblings recall/query_layer, so an agent can differentiate without opening a schema.

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 names the alternatives (keyword-based recall/query_layer) and states the condition that selects this tool (when there is no keyword overlap but conceptual relation is expected). It stops short of explicit when-not/exclusion phrasing, but the routing signal is clear.

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