Vaultwarden Metadata Backfeed

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

Annotations only declare readOnlyHint=true, so the description carries most of the burden and does deliver the critical behavior: this call always refuses and never mutates the metadata source. It stops short of saying what the refusal looks like (error vs. structured result), though an output schema exists to cover the return shape.

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 key action is front-loaded in a short sentence, which is good, but the trailing 'CONCEPT:VW-KG.ingest.metadata-only' token is internal taxonomy that conveys little to an agent and reads as leftover annotation rather than useful prose.

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 no-argument refusal tool with an output schema, the description covers the essential 'it will not succeed' fact but leaves open what the caller receives and whether any workflow should ever call it. It is minimally adequate rather than complete.

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?

The tool takes zero parameters, so there is no parameter meaning for the description to add. Baseline 4 applies; the schema is trivially complete with additionalProperties=false.

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 states a concrete verb ('Refuse') but the object ('a backfeed') is internal jargon that an agent cannot map to a user-facing operation. The second clause explains why the refusal happens, yet it never clarifies what the tool is for relative to the sibling 'vaultwarden_metadata_snapshot', which is presumably the readable counterpart.

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 explicit when-to-use or when-not-to-use guidance and no mention of the alternative (metadata_snapshot) for actually obtaining metadata. The read-only rationale implies the tool should not be used for ingestion, but the agent must infer this rather than being told.

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