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

Annotations already mark the tool read-only and non-destructive; the description adds that results come from an AI semantic/vector pipeline and that conversation_id enables follow-ups. It does not detail pagination, latency, or rate limits, but those are secondary given the safety annotations and output schema.

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?

Three short sentences with the core action front-loaded. The Typesense/embedding sentence is somewhat implementation-specific but earns its place by setting expectations about semantic matching; there is no filler.

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 the output schema available and all parameters documented in the schema, the description plus annotations give enough to invoke correctly. It lacks explicit guidance for choosing among sibling search tools, but that gap is about routing rather than completing this tool's contract.

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?

The schema already describes all four parameters with 100% coverage, so the bar is a baseline of 3. The description only reinforces natural-language querying and conversation follow-up, adding no new format, default, or filter semantics.

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 first sentence names the exact verb and resource ('Search documents') and adds scope ('across all accessible workspaces'), plus the natural-language/semantic mode. It is clear enough to be mistaken for neither list_documents nor simple keyword search, though it does not explicitly name sibling search 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?

The description implies this is the tool for natural-language/semantic search across all workspaces and for follow-up queries, but it never states when to use search_files or search_notes instead. No exclusions or alternative routing are provided.

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