search_memory_semantic

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

With no annotations available, the description carries the full behavioral burden and does it well: it discloses the external dependency on Ollama and nomic-embed-text, the failure mode when unavailable, the semantic behavior ('no keywords'), and the audit-log purpose of the llm parameter. This is substantial non-obvious context beyond the tool name.

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 compact and well-structured: the core behavior and prerequisite are front-loaded, the fallback is stated immediately, and the parameter list is scannable. No sentences are wasted; each earns 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 4-parameter tool with no annotations, the description covers prerequisites, failure behavior, fallback, parameter semantics, and scope handling. Since an output schema exists, the lack of explicit return-format details is not a gap. The description leaves an agent with everything needed to invoke 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?

Even though the JSON schema has no property descriptions (0% coverage), the tool description fully documents all four parameters: query as a natural-language description, project as an optional scope with empty meaning all, limit as a max-results count with default 5, and llm as the audit-log name. This fully compensates for the missing 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 clearly defines the tool as a meaning-based semantic search over notes, explicitly distinguishing it from keyword search by stating it 'finds related notes that share no keywords.' This makes it easy to differentiate from siblings like search_memory and read_memory without inspecting schemas.

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?

It gives explicit when-to-use guidance: semantic search is appropriate when a natural-language query is needed, and if Ollama/model prerequisites are not met, the description directly instructs to 'use search_memory instead.' This is a clear, actionable fallback with no ambiguity.

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