vault_sign

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

With no annotations, the description carries the full burden and does so well: it discloses that the key is never returned, that every signature requires owner approval, that the owner sees the data plus its sha256, the 256 KiB ceiling, and exactly what is returned (signature, public key, algorithm). It stops short of describing rejection/failure behavior or what happens when the size limit is exceeded.

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?

Four short sentences, zero waste, with the core action and the strongest constraint (key never returned) front-loaded. Every sentence carries a distinct fact: action, approval model, return values, size limit.

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 non-destructive-looking signing tool with no output schema and no annotations, the description supplies return fields, the approval model, and size constraints — enough to call it correctly. The remaining gap is error/rejection behavior and whether signing is deterministic, which an agent would want for retry logic.

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, but the description adds real semantics on top: the 256 KiB cap on data and the 64 KiB threshold at which text is shown to the owner in full. `purpose` is reinforced as owner-visible, though its operational effect is already in the schema.

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?

States a specific verb and resource ("Sign data with a vaulted signing key") and immediately scopes it with the constraint that the key is never returned. That is clearly distinct from sibling operations like vault_call, vault_pay, and vault_ssh_exec, so an agent can select it without reading further.

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?

Usage is implied by the purpose (sign a payload held by the vault) rather than explicitly stated; there is no guidance on when to prefer this over vault_call or the other siblings, and no exclusions. The approval flow is described, which gives the agent context on cost/latency, but it is not framed as a selection rule.

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