memory_search

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

No annotations are provided, so the description carries the full burden. It discloses the lazy-loading of the ONNX model and sqlite-vec on first call, the default scope-filtering behavior, and the optional min_length filtering. These are meaningful behavioral traits that an agent would not know from the schema alone.

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?

The description is dense and front-loaded: it opens with the core semantic search capability, then covers scope filtering, optional parameters, lazy-loading behavior, and the relationship to project_search. Every sentence adds distinct value with no filler or redundancy.

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 no annotations and no output schema, the description covers the invocation semantics, default behavior, optional filtering, and alternative tooling. It does not enumerate the exact fields returned for each memory, but 'top-k memories by cosine similarity' plus the schema's parameter definitions give an agent sufficient grounding to call it correctly.

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?

With schema coverage at only 50%, the description substantially compensates by explaining the semantics of scope (auto-infer vs. 'global' vs. explicit project), category (exact-match filtering), min_length (with a concrete example value), and cwd (project inference). It also clarifies top_k via 'Returns top-k memories'. This goes well beyond the sparse schema descriptions.

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 states a specific verb and resource: 'Semantic search over the shared vector memory store' using a named embedding model and sqlite-vec KNN, returning top-k memories by cosine similarity. It also explicitly distinguishes itself from the sibling keyword tool project_search, making its role clear among many memory-related siblings.

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 explains when to use this tool versus project_search ('Complements keyword search... for recall across agents') and gives concrete operational guidance on scope filtering, category, and min_length. It does not explicitly list exclusions or 'don't use when' scenarios, but the context is clear and actionable.

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