mneme_search

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

With no annotations provided, the description carries full burden. It discloses the retrieval algorithm (FTS5 BM25, Turkish normalization), optional filters, and important output details (cards array with content_hash, trust, confidence, backend field, backends_used array). It also notes backward compatibility for 'hits', adding transparency without contradictions.

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 efficiently structured: main purpose, algorithm, filters, output details. It is concise with no fluff, though it could be organized into bullet points for easier parsing.

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 no output schema, the description thoroughly explains the output structure (cards with fields, backends_used). It covers filters and backward compatibility. Missing details like snippet format or pagination, but top_k covers result count.

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 coverage is low (25%), so description must compensate. It explains 'query' as free-text, 'top_k' default 10 max 50, and implies filters for date and type. However, it does not detail 'min_query_length' and misses that the schema already defines filter enum values. Adds some value but not enough for full clarity.

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 it performs retrieval over the vault with FTS5 BM25 and Turkish normalization. It specifies optional filters and returns ranked hits with snippets. However, it does not explicitly differentiate from sibling tools like mneme_recall or mneme_timeline, relying on the name to imply 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?

The description mentions optional date and frontmatter type filters but provides no guidance on when to use this tool versus its siblings (mneme_prime, mneme_recall, etc.). There is no explicit alternative naming or when-not-to-use advice.

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