search

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

Annotations already cover the read-only, non-destructive safety profile. The description adds meaningful behavior context: it is a 'plain dense semantic search' (not hybrid or reranked), and it emphasizes speed and simplicity. This goes beyond merely restating annotations, though it stops short of detailing filter syntax or limit behavior.

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?

Two dense sentences deliver scope, routing guidance, and behavioral characterization with zero filler. The main instruction is front-loaded and the comparison to alternatives is placed near the end without bloat.

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 simple, read-only search tool with an output schema present, this description sufficiently identifies the operation and key distinguishing traits. It does not repeat return-value details (correctly leaving that to the output schema), and the sibling context is large but the routing guidance handles that well. Minor gaps around filter payload details prevent a 5.

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 0%, so the description carries the burden. It clarifies that `collection` is the target collection and `filters` are optional payload filters, and query is implied by 'semantic search.' However, it does not explain the format or constraints of `filters` or highlight `limit` semantics, leaving some ambiguity for the agent.

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 clear, specific verb/resource pair: 'dense semantic search over a collection' with optional payload filters. It distinguishes this from siblings like search_hybrid and search_rerank by scoping it to plain dense search without fusion or reranking.

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 explicitly says when to use this tool ('fast, simple similarity search when hybrid fusion or reranking isn't needed') and when not to ('for most RAG questions, prefer get_context or search_hybrid instead'). This is exemplary routing guidance.

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