Skip to main content
Glama

Update Workspace

update_workspace

Use this for structured data. To add an agent-specific operational learning, call append_learning instead.

The app reads inputs: excluded, mailbox, entity_type, discovery_mode, watcher_context, content_calendar, destination; outputs: ideas, drafts, published, digests, insights. Values there must fit the app's shape (a rejected write shows it); for your own data, use another key.

operation='read': Name section and key to get back just that entry; section alone returns that section; neither returns the full workspace ({inputs, outputs}). An entry that was never written comes back as an empty section. The full form re-sends every entry, so name the entry when you know which one you want. operation='update': Requires section, key, and a non-null value. Sets workspace[section][key] = value. operation='append': Requires section, key, and a LIST value. Atomically extends the existing list at workspace[section][key] with value's items (creating it if absent). Use this to accumulate into a list — a digest entry, new calendar topics, freshly-created draft records — without reading, concatenating, and rewriting the whole array yourself (which races other writers). Errors if the current value isn't a list (use 'update' to replace it). operation='delete': Requires section and key. ALWAYS confirm with the user before calling — this is destructive. Shape depends on the operation. On read, {'success': True, 'agent_id': ..., 'workspace': {'inputs': {...}, 'outputs': {...}}}, with 'workspace' holding only the section — or only the one section/key entry — you named. On update or delete, {'success': True, 'agent_id': ..., 'workspace_keys': {'inputs': [...], 'outputs': [...]}}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
keyNoThe key to set, extend, or delete (required for update/append/delete; optional narrowing for read, where it also needs section)
valueNoValue to store (required for update; must not be None — use operation='delete' to remove a key). Name any outside resource a run reads (a Google Sheet, doc, file, URL) by the identifier its tool takes (the spreadsheet ID and tab, the URL), not only by its title — a later run doesn't see this chat. For append, a list of items to add to the existing list.
sectionNoWhich workspace section — 'inputs' or 'outputs' (required for update/append/delete; optional narrowing for read)
agent_idYesID of the agent
operationYes'read', 'update', 'append', or 'delete'

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / value / description
      Previous value: -"Value to store (required for update; must not be None — use operation='delete' to remove a key).\nFor append, a list of items to add to the existing list."New value: +"Value to store (required for update; must not be None — use operation='delete' to remove a key). Name any outside resource a run reads (a Google Sheet, doc, file, URL) by the identifier its tool takes (the spreadsheet ID and tab, the URL), not only by its title — a later run doesn't see this chat.\nFor append, a list of items to add to the existing list."
  2. Changed3 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
      +  "description": "ID of the agent",
      +  "type": "integer"
      +}
    • removedInput schema / properties / task_id
      Removed value: -{
      -  "description": "ID of the task",
      -  "type": "integer"
      -}
    • changedInput schema / required
      Previous value: -[
      -  "task_id",
      -  "operation"
      -]New value: +[
      +  "agent_id",
      +  "operation"
      +]
  3. First observed

TDQS

A3.9/5.0
Behavior2/5

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

The description is unusually rich behaviorally — atomic append vs read-concat-rewrite race, append failing on non-list values, empty sections for never-written entries, full-form read resending every entry, rejected writes showing app shape. However, it calls delete 'destructive' and demands user confirmation, which directly contradicts the destructiveHint=false annotation; that inconsistency is the reason this is not scored higher.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Content is front-loaded on the two sections and mostly earns its place, but the description is bloated: XML-style <summary>/<returns> wrappers inside a description field, and operation semantics that duplicate the schema. A tighter form would communicate the same routing and behavior in fewer words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description embeds a <returns> block explaining the response shape per operation (workspace vs workspace_keys), plus per-operation preconditions and failure modes. For a 4-mode mutation tool, an agent has everything needed to call it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description restates the per-operation parameter requirements (section/key/value for update, list value for append) that the schema already documents, adding little new parameter meaning beyond the schema's own text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb(s)+resource (read/update/append/delete entries in an agent's workspace) and immediately explains the two sections and their rendering. It explicitly distinguishes itself from `record_search_results` for bulk entity sets and from `append_learning` for operational learnings, so an agent can route 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.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit when-to-use and when-not-to-use guidance: use record_search_results for any bulk people/companies set, append_learning for operational learnings, and this tool for structured data. Per-operation requirements (append only for lists, delete requires confirmation) further pin down usage.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources