Vaultwarden Metadata Snapshot

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

readOnlyHint=true is already supplied, and the description adds genuine context beyond it: it enumerates exactly what the payload contains (opaque identifiers, type codes, lifecycle timestamps, counts, typed relationships) and explicitly excludes names, notes, usernames, passwords and URIs. That privacy/redaction posture is the kind of behavioral detail annotations cannot convey, though the sentence about commit/checkpoint authority is opaque and leaves the mutation boundary unclear.

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 content-bearing sentences are front-loaded and efficient, but the 'Scion SDK source_sync is the only graph commit, checkpoint and reconcile authority' sentence and the machine tag 'CONCEPT:VW-KG.ingest.metadata-only' consume space without helping an agent decide or invoke. Roughly a third of the text does not earn its place.

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 only two optional parameters, an output schema present, and a readOnlyHint, the definition covers enough to make a call. What is missing for completeness is the relationship to vaultwarden_metadata_backfeed and what a 'delta' actually continues from, which matters for correct incremental use.

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%, so both 'mode' (delta/full) and 'checkpoint' are already documented in the schema. The description adds no semantics for delta-vs-full behavior or how the checkpoint timestamp is applied, so the baseline of 3 applies.

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 names a verb ('Serve') and a resource ('certified metadata-only source projection') and clarifies that it emits identifiers, type codes, timestamps, counts and typed relationships rather than secrets. But 'projection' and 'CONCEPT:VW-KG.ingest.metadata-only' are internal jargon an agent cannot map to a concrete Vaultwarden concept, and the description never distinguishes this from the sibling vaultwarden_metadata_backfeed.

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?

There is no statement of when to call this instead of metadata_backfeed or the various get_* read tools. The only routing-style sentence says Scion SDK source_sync is the sole authority for graph commit, checkpoint and reconcile, which implies what this tool is not for, but that is negative inference rather than positive guidance and sits awkwardly beside the tool's own 'checkpoint' parameter.

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