list_trashList the documents in the user’s Trash (their own and every team they belong to), each restorable with restore_document until it is purged 30 days after deletion. Returns id, name, library, why it is there, when it was deleted, and when it goes.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| trash | Yes | The documents that can still be restored. |
Changes observed during successful MCP inspections.
Output schema / properties / trash / items / properties / reasonAdded value: +{
+ "description": "Why it is in the Trash: \"deleted\" by someone, or \"empty\" (moved automatically after 30 days with no content).",
+ "enum": [
+ "deleted",
+ "empty"
+ ],
+ "type": "string"
+}Output schema / properties / trash / items / requiredPrevious value: -[
- "id",
- "name",
- "library",
- "deletedAt",
- "purgeAt"
-]New value: +[
+ "id",
+ "name",
+ "library",
+ "reason",
+ "deletedAt",
+ "purgeAt"
+]Output schema / properties / trash / descriptionPrevious value: -"The diagrams that can still be restored."New value: +"The documents that can still be restored."Output schema / properties / trash / items / properties / id / descriptionPrevious value: -"The diagram id."New value: +"The document id."Output schema / properties / trash / items / properties / name / descriptionPrevious value: -"The diagram name."New value: +"The document name."Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: the 30-day purge window, the fact that entries remain restorable until then, and the cross-team scope of what is returned. It stops short of mentioning pagination or result limits.
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?
Two sentences, zero filler. The scope and restorability constraint are front-loaded, and the retention rule is attached directly to the concept it qualifies rather than buried in a trailing clause.
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, the description need not explain return values, yet it still summarizes the key fields. Combined with the purge timeline and the cross-team scope, an agent has everything required to decide whether to call this and what it will get back.
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 no parameters, so per the rubric the baseline is 4. The description adds no parameter information, but none is needed — it instead enumerates the returned fields, which is orthogonal to the (empty) input schema.
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?
States a specific verb (List) and resource (documents in Trash), and pins down scope precisely: the user's own trash plus every team they belong to. An agent can distinguish this from find_documents or list_templates without opening a schema.
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 retention clause ('purged 30 days after deletion') implies the urgency context for calling it, and it names restore_document as the follow-up action, effectively routing the agent to the sibling that acts on these results. It does not, however, state explicitly when to prefer this over find_documents or what to do if the trash is empty.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.