Vault Ask

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

Beyond the readOnly and idempotent annotations, the description discloses meaningful behavior: it returns a how-to-enable message when not configured, never errors, and changes behavior when HIVE_SYNTH_MODEL is set. This gives the agent accurate expectations for unconfigured environments.

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 front-loaded with the core purpose and then efficiently covers fallback behavior, configuration prerequisites, and the sibling alternative. Every sentence serves a distinct purpose without redundancy.

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 the output schema exists and the tool has optional synthesis behavior, the description fully covers prerequisites, degraded mode, configuration, and when to use a sibling tool. An agent has everything needed to decide whether and how to call it.

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 the baseline is 3. The description adds value by emphasizing use of the `question` parameter over `query` or `prompt`, which helps agents avoid common naming mistakes.

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 uses a specific verb ('Ask') and resource ('vault') with a concrete output ('source-cited synthesized answer' or 'relevant vault sections'). It clearly distinguishes itself from sibling vault_search by framing this as natural-language / semantic retrieval versus keyword / regex lookup.

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 states exactly when to use the tool (natural-language questions, semantic retrieval/RAG) and explicitly says to use vault_search instead for keyword/regex lookups. It also covers the disabled-by-default state, prerequisites, and configuration needed for synthesis.

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