Search Memory

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so safety is covered. The description adds genuinely new behavior: results are ranked, memories are not mutated, and retrieval is gated by the user's memory setting and tenant policy — policy/auth context not derivable from annotations.

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 tight sentences, front-loaded with the use case followed by behavioral guarantees. Minor redundancy: "without changing them" restates the readOnlyHint annotation, so one clause 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?

For a 2-parameter read tool with full schema coverage, no output schema, and complete annotations, the description covers purpose, gating behavior, and mutation safety. It does omit return shape (fields, score/rank format) and pagination or empty-result behavior, which an agent might want.

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 query ("What to recall") and top_k ("How many memories to return") are already documented. The description only implies ranked return ordering and adds no syntax, format, or default guidance beyond the schema; 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 specific verb (recall) and resource (the authenticated user's Bee memory) and enumerates the content classes it covers: facts, preferences, projects, skills. This clearly separates it from the sibling write path (bee_memory_add) and from document-oriented siblings like bee_documents_search 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?

"Use to recall facts, preferences, projects, or skills from the authenticated user's Bee memory" gives a clear trigger context, but it names no alternatives and states no exclusions (e.g., when to prefer bee_documents_search or bee_chat context). Clear context without routing rules.

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