Search brain

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description goes well beyond them: it discloses the retrieval pipeline (semantic + BM25, MiniLM cross-encoder rerank, two-hop related_to expansion), the fields attached to each result (addedBy, versionCount, truncated), and the truncation behavior. That is exactly the kind of operational context an agent needs to interpret results correctly.

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?

Front-loads purpose, then query guidance, then retrieval mechanics, then follow-up routing rules. Six sentences with no repetition of schema or annotation content, and each carries actionable information.

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?

With no output schema, the description fills the gap by naming the salient result fields and the truncation signal, and it explains how to handle each follow-up case. Nothing material for a correct call or correct result interpretation is missing.

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 100%, so baseline is 3, but the description adds real meaning: it constrains the query parameter's shape (focused key terms, not the whole user message) and reinforces that brain must come from list_brains. It does not explain kind or entityType, which the schema already handles 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?

Opens with a specific verb+resource ("Search saved Brain memories") and immediately clarifies what a memory is (singular fact or short Markdown mini-doc). This clearly separates it from siblings like get_memory (single fetch by id), list_brains (enumeration), and the mutation tools.

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?

Gives explicit query-construction advice ("short, focused query with the key people, entities, preferences, or topics... not the full user message") and hard routing rules: call get_memory_versions when versionCount > 1, call get_memory when truncated: true, and always pass brain from list_brains. Both when-to-use and which-alternative conditions are stated.

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