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

With no annotations, the description carries the full burden; it does disclose the retrieval mechanism and that multiple matching facts come back, which is useful behavioral context. It does not say whether results are ranked, deduplicated, truncated by limit, or how include_sources affects payload size, leaving notable gaps for a read operation with nine parameters.

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 short sentences, mechanism first, return shape second, with no filler. The closing clause 'for the agent to digest' is mildly decorative but does convey the multi-fact return nature.

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?

Nine parameters with non-trivial scoping (thread vs agent, task pools, source kinds) are fully documented in the schema, and no output schema exists, so the description should say more about what the returned facts look like. It gestures at multiplicity but omits ranking, format, and result-size 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 description coverage is 100%, including the scope/thread_id semantics and memory_filters pointer, so the schema does the heavy lifting. The description adds no parameter-level meaning beyond what is already in the schema.

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 and resource (search memory) plus the mechanism (embedding retrieval, no LLM selection), which implicitly separates it from memory_recall's LLM-based selection. It never names the sibling, so the differentiation is left partly to inference.

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 phrase 'without LLM selection' hints at when this is preferred over memory_recall, but there is no explicit when-to-use or when-not-to-use guidance and memory_add/memory_filters are not addressed. Usage must be inferred from the mechanism description.

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