memory_semantic_search

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

Despite no annotations, the description fully discloses behavior: pure read, local embeddings, first-call latency (1-2s), and condition of no results if index not built, with a pointer to memory_stats for build state.

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?

Concise yet comprehensive: single paragraph with clear sections for purpose, returns, usage guidance, behavior, and parameters. No unnecessary words.

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?

Given the tool's complexity and the presence of an output schema, the description covers all essential aspects: purpose, usage scenarios, behavioral traits, parameter details, and guidance on related tools. Complete and well-rounded.

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?

The description adds meaning beyond the schema by explaining query as free-text required non-empty, and limit as max results range 1-50 with default 10. Schema coverage is 0%, so description compensates adequately.

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 clearly states 'Vector-similarity search over stored memory entries using local embeddings' and specifies returned data (ranked matches, similarity scores, key/value/tag). It differentiates from siblings like memory_recall and memory_search.

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?

Explicitly provides 'USE WHEN' and 'NOT FOR' sections with named alternatives, including guidance on when not to use (exact-key or substring lookup) and performance comparison (slower than memory_search).

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