Plan Deduplication

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

Beyond the annotations, the description discloses the output shape ("item ids and counts only") and a safety gate (confirm: true required before applying or rotating, and no automatic application of a loose plan). This is meaningful behavioral context that the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false) do not convey.

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 constraints are front-loaded after the title restatement, and each sentence carries information, but the redundant parenthetical "(vaultwarden_maintenance)" and the trailing CONCEPT tag add no decision value for the agent.

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?

An output schema exists, so return values need not be explained, and the confirm gate is covered. However, for a non-idempotent, open-world mutation orchestrator with an opaque params_json, the description leaves unclear how actions are selected and how it relates to its three maintenance siblings.

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?

With a single params_json blob at 100% schema coverage, the schema only says "JSON object of parameters for the action," so the description should enumerate the keys. It does mention confirm: true, which adds real key-level meaning, but it never documents which other keys select between plan/apply/rotate/generate.

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 first clause names a verb and resource ("Plan deduplication"), but the follow-on sentence, "Plan/apply vault deduplication and rotate or generate passwords," blurs the scope so it now appears to overlap three siblings: apply_deduplication, rotate_password, and generate_password. An agent cannot tell from the description alone whether this tool only plans or also performs those mutations.

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?

It states that applying deduplication or rotating a password requires confirm: true and that a loose plan is never auto-applied, but that is a rule, not routing advice. It never says when to call this tool versus vaultwarden_maintenance_apply_deduplication or rotate_password, even though those siblings exist for exactly that purpose.

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