Get Item

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

Annotations already declare readOnlyHint/idempotent/non-destructive, but the description adds material context the annotations cannot: get_item returns plaintext (decrypted) item contents and the caller must not log or echo them. That is a genuine, decision-relevant disclosure. It falls short of 5 because it says nothing about required access, behavior when the item is missing, or trash state.

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 tool-specific content is a single short line; the remainder is concept-level boilerplate about create_item, edit_item, move_to_trash and call_operation that does not earn its place in a get_item definition. It is front-loaded with the name, but the payload is diluted by unrelated actions.

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 an output schema present, return structure need not be described, and the plaintext handling warning covers the main risk. Still missing for a read tool: what identifier form to pass in params_json and what happens on a missing or trashed item, which the caller must infer.

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 single parameter is an opaque params_json blob whose schema description ("JSON object of parameters for the action") gives no key-level detail; schema coverage is nominally 100%, so the baseline of 3 applies. However, the description does not compensate by naming the cipher id that get_item presumably requires, leaving the caller to guess the payload shape.

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 name and first sentence ("Get item (vaultwarden_ciphers). Read and write vault items (ciphers)") imply retrieval of a single cipher, but the body is family-level boilerplate that lumps get_item with list/create/edit/move_to_trash. It never differentiates this tool from close siblings such as vaultwarden_get_cipher, vaultwarden_get_cipher_details, or vaultwarden_ciphers_list_items, so an agent must infer which retrieval tool to pick.

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?

The description never says when to use this tool rather than the list or other get variants, nor what condition selects it. The only routing statement ("Every other ciphers API route is reachable by its route name via call_operation") is about the escape hatch, not about choosing get_item.

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