recover_document

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

With no annotations at all, the description carries the full burden of behavioral disclosure, and it delivers only the bare action. It does not say what state the document returns to, whether restoring an already-active or non-existent document errors, whether the action is idempotent or undoable, or what permissions/company scoping apply. For a destructive-adjacent mutation, that is a substantial gap.

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 single sentence is front-loaded and free of waste, but it reads as under-specification rather than disciplined concision. Nothing is redundant, yet the brevity leaves the operation's preconditions and parameters unexplained.

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 3-parameter mutation with no annotations and no output schema, the definition should explain the kind/id pairing, the company scoping default, and what the restore actually does. None of that is present, and the description is written in a different language from the tool names and sibling set, adding a small comprehension cost.

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 coverage is only 33%: id and kind have no schema descriptions, and the description compensates for neither. In particular the `kind` enum (issued vs received, default "issued") is a critical choice omitted from the description — an agent could restore the wrong document type by leaving the default — and the required `id` is never explained as the trashed document's identifier.

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?

"Ripristina un documento dal cestino" states a specific verb (restore) and resource (a trashed document), which is clearly distinct from siblings like delete_received_document or list_deleted_documents. It stops short of naming the sibling that surfaces recoverable documents, so the agent gets the purpose but not the surrounding workflow.

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 guidance on when to use this tool versus list_deleted_documents (to find a deleted document) or get_received_document (to inspect one before restoring). No preconditions are stated, such as the document having to be in the trash or belonging to the active company, and no mention of whether the operation is reversible.

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