search_journal

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

With no annotations provided, the description bears full responsibility for behavioral disclosure. It explains that scores are cosine similarities from a multilingual-e5 model clustering in a narrow band (~0.80-0.89), warns that high scores alone do not imply relevance, and notes that minScore lacks a universal cutoff. This gives the agent essential context for interpreting results.

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 concise, with three short paragraphs that each serve a distinct purpose: stating the tool's function and output, providing usage guidance, and clarifying score interpretation. Every sentence adds value, and the most critical information is front-loaded in the first sentence.

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 absence of an output schema, the description fully enumerates what is returned (markdown snippets with source paths, sections, scores, excerpts). It also covers how to use parameters and interpret results, making the tool's behavior complete without needing additional documentation.

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 0%, so the description must compensate. It explains the section parameter's purpose for narrowing vs. broad discovery and details the meaning and limitations of scores and minScore. However, it does not explicitly describe the 'limit' parameter beyond its schema constraint (integer, max 50), which is acceptable but not fully compensating.

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 explicitly states the tool searches private journal entries semantically and returns LLM-readable markdown snippets with source paths, sections, scores, and excerpts. This clearly distinguishes it from siblings like write_journal, read_journal, and list_journal by focusing on semantic search rather than direct access or listing.

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 provides clear guidance on when to use the section parameter ('narrow recall when the intent is known') and when to omit it ('for broad discovery'). It also cautions about interpreting scores and minScore, helping the agent decide when to rely on the tool's output. While explicit sibling comparisons are absent, the usage advice is sufficient.

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