Vault Search

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered elsewhere. The description adds only the unusual invocation channel (SPA/app context), and says nothing about result shape, ranking behavior across the three modes, or cost – though an output schema exists to cover returns.

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 short sentences, front-loaded with the resource and the distinguishing qualifier, with no filler. Slightly cryptic rather than verbose, but structurally efficient.

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?

Annotations, a full-coverage schema and an output schema carry most of the burden, so this is close to adequate. The main gap is that the description positions itself as an internal app tool invisible to the LLM while being offered as an LLM tool, leaving the agent without a clear rule for when it should be chosen over `search`.

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 100%, with all three parameters documented including the mode enum and limit default. The description adds no meaning beyond that – notably it does not explain what keyword vs semantic vs hybrid actually do or when to pick each.

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?

"Search the vault" is a concrete verb+resource, but it does not separate this tool from several siblings with overlapping purpose (`search`, `query_documents`, `browse_vault`). The "(app-only)" qualifier hints at a different consumer but never states how results differ from those siblings, so the agent cannot distinguish it on capability alone.

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 does supply invocation context (called by the SPA search bar via `app.callServerTool()`) and states it is "Not visible to the LLM," which effectively tells an agent to avoid it. However, it never names the alternative the agent should use instead, so routing away is left to inference.

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