Discard a pending memory in the Inbox, removing it from view and deleting its embeddings.
Args:
memory_id: The ID of the memory (e.g., 'mem_123').
| Name | Required | Description | Default |
|---|---|---|---|
| memory_id | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosure. It clearly states the destructive side effect of deleting embeddings and that the memory will no longer be visible in the Inbox. It stops short of saying whether the operation is permanent or reversible, but 'discard' and 'deleting' already signal data loss.
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 description is compact, front-loaded with the core purpose, and spends exactly one line on the parameter. Every sentence contributes information; there is no filler or repetition of schema fields.
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 one-parameter tool with an output schema and low complexity, this description covers what the tool does, what effect it has, and which ID to pass. The main omission is a clearer distinction from delete_memory, but that gap is more about usage routing than about invoking the tool correctly.
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 description coverage is 0%, so the description must compensate. It identifies memory_id as 'The ID of the memory' and provides a concrete format example ('mem_123'), which is meaningful beyond the schema's bare title 'Memory Id'. For a single simple string parameter, this is adequate guidance.
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 uses a specific verb ('Discard') and identifies a precise resource state ('a pending memory in the Inbox'). It also clarifies the observable effects ('removing it from view and deleting its embeddings'), which sets it apart from sibling tools like approve_memory or delete_memory without requiring schema inspection.
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 intended context is implied: the tool is for pending memories currently in the Inbox. However, it does not explicitly contrast with alternatives such as delete_memory or approve_memory, nor does it state when not to use it. An agent could infer usage, but there is no explicit routing guidance.
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.
Most tools map cleanly to distinct operations such as semantic search, date search, inbox approval/discard, and tag listing. The main ambiguity is between save_memory and upsert_memory, both of which can create memories with similar arguments; get_memory/get_document and delete_memory/discard_memory are also distinguishable mainly by ID prefix or inbox state.
The names are consistently lowercase snake_case and verb-first, which makes the set fairly predictable. Minor deviations include search_by_date breaking the verb_noun pattern, get_inbox/get_all_tags acting as list operations while list_memories uses 'list', and upsert_memory being an unusual verb.
At 13 tools, the surface is well-scoped for a memory/document vault: create, upsert, update, retrieve, list, semantic and date search, tags, and inbox workflow are all represented without excessive granularity or redundant filler.
The toolset covers the core memory lifecycle well, including save, upsert, update, get, search, list, delete, and inbox approval/discard. Minor gaps remain: update_memory only accepts mem_ IDs, so documents found via search have no document-specific update path, and workspace management is only handled through optional name strings.