history

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

No annotations are provided, so the description carries the full burden and does meaningful work: it declares 'Read-only' and discloses the quarantine withholding rule (rows retained, text/value suppressed unless the flag is set). It omits pagination, ordering of ties, and whether retired/deleted keys still appear, which keeps it short of a 5.

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 tight sentences, front-loaded with the core purpose and scope before the read-only and quarantine caveats. Only the 'plain vector store cannot produce' clause is expendable.

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 no output schema and no annotations, the description adequately covers purpose, safety profile, and the quarantine behavior, and implies row shape ('its row with its text and value withheld'). It stops short of describing the returned record fields or result size for a key with many versions.

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 0%, so the description must compensate, and it does for the non-obvious parameter: `include_quarantined` is explained by its effect (quarantined versions surface with text and value withheld unless set). `key` is used but not defined, though its meaning is self-evident.

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 resource and output: the full validity timeline of every value a `key` has held, in event-time order. This is clearly distinguishable from `get` (current value), `as_of` (point-in-time), and `provenance`, though it never names those siblings explicitly. The 'audit trail a plain vector store cannot produce' clause adds flavor rather than routing guidance.

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 audit-trail framing — an agent can infer this is for inspecting a key's value history — but there is no explicit when-to-use, when-not, or pointer to `get`/`as_of`/`provenance` as alternatives. Nothing misleading, just unstated.

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