Skip to main content
Glama
soil-dev

capsulemcp

by soil-dev

batch_update_party

Update 1–50 party records in parallel via a single call, returning per-item results and a summary. Ideal for bulk edits, mass reassignments, or metadata corrections.

Instructions

Update 1–50 parties in parallel. Same input shape as update_party but wrapped in an items array. Use this — not N sequential update_party calls — for any homogeneous multi-record write (mass owner reassignment, bulk metadata corrections, etc.). Capsule has no batch-write API, so the connector fans out parallel HTTP requests with a default concurrency cap of 5 (configurable via CAPSULE_MCP_BATCH_CONCURRENCY). Returns { results: [{ok, ...} per item], summary: {total, succeeded, failed} }. Partial failures are possible — Capsule has no rollback, so successful items stay applied even if other items 4xx. Read the per-item result array to know which ones need follow-up.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
itemsYesArray of 1–50 update_party inputs. Each item is the same shape as a single update_party call — id is required, every other field is optional. Capped at 50 so a single tool call can't burn an outsized share of Capsule's hourly per-token rate budget (~4000 req/h).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.3.1
    • changedInput schema / properties / items / items / properties / emailAddresses / items / properties / address / pattern
      Previous value: -"^(?!\\.)(?!.*\\.\\.)([A-Za-z0-9_'+\\-\\.]*)[A-Za-z0-9_+-]@([A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"New value: +"^(?:[A-Za-z0-9_'+\\-]+\\.)*[A-Za-z0-9_'+\\-]*[A-Za-z0-9_+-]@(?:[A-Za-z0-9][A-Za-z0-9\\-]*\\.)+[A-Za-z]{2,}$"
  2. Changed4 schema fields changedv2.3.0
    • removedInput schema / properties / items / items / properties / fields / items / properties / value / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / items / items / properties / fields / items / properties / value / type
      Added value: +[
      +  "string",
      +  "number",
      +  "boolean",
      +  "null"
      +]
    • changedInput schema / properties / items / items / properties / fields / items / required
      Previous value: -[
      -  "value"
      -]New value: +[
      +  "definitionId",
      +  "value"
      +]
    • addedInput schema / properties / items / items / required
      Added value: +[
      +  "id"
      +]
  3. Changed13 schema fields changedv2.1.2
    • removedInput schema / properties / items / items / properties / addresses / description
      Removed value: -"APPEND-ONLY: items are merged into the existing list, never replaced. For atomic add/remove/replace use add_party_address and remove_party_address_by_id. The `country` field is mapped through Capsule's country dictionary — see `add_party_address.country` for the dictionary edges (small canonical-English-name list; inputs not in the dictionary are REJECTED with 422, not silently dropped)."
    • removedInput schema / properties / items / items / properties / addresses / items / properties / country / description
      Removed value: -"Country name. Capsule validates this against a small canonical-English-name dictionary; inputs not in the dictionary are REJECTED with 422 'address.country: unknown country' (NOT silently passed through or normalised). Probed examples — accepted: `United States`, `United Kingdom`, `Czechia`, `Germany`. Aliased: `USA → United States`. Rejected: `United States of America`, `Czech Republic` (use `Czechia`), `UK`/`Britain` (use `United Kingdom`), `Deutschland` (use `Germany`). Empty string is accepted and stored as `null` — a de-facto 'clear' shape. To discover an accepted name, read an existing party that already has the country set."
    • removedInput schema / properties / items / items / properties / emailAddresses / description
      Removed value: -"APPEND-ONLY: items are merged into the existing list, never replaced. For atomic add/remove/replace use add_party_email_address and remove_party_email_address_by_id. Passing `[]` here is a silent no-op (does not clear the list and does not advance updatedAt)."
    • removedInput schema / properties / items / items / properties / fields / description
      Removed value: -"Set custom field values on this record. PARTIAL UPDATE: only the definitions you list are touched; any field NOT in this array is left unchanged. Discover available definitions via list_custom_fields; read current values via get_party with embed='fields'."
    • removedInput schema / properties / items / items / properties / fields / items / properties / definitionId / description
      Removed value: -"The custom-field definition id from list_custom_fields. Identifies which field on the entity to set."
    • removedInput schema / properties / items / items / properties / fields / items / properties / value / description
      Removed value: -"The new value. String for TEXT / DATE / LIST / LARGE_TEXT / LINK fields, number for NUMBER fields, boolean for BOOLEAN fields. Clearing: pass null for TEXT / NUMBER / DATE / LIST (Capsule removes the row). BOOLEAN does NOT accept null (Capsule returns 422 'invalid type for field'); use `value: false` instead. Note BOOLEAN fields are observably **two-state**: a row exists with `value: true`, or no row exists. Setting `value: false` removes the row entirely — readers should treat absent BOOLEAN rows as equivalent to false. Tri-state BOOLEAN semantics (true / false / unknown) are not achievable through Capsule's API. Audit-log noise: sending value=null on a field that's already empty/cleared is accepted by Capsule but still bumps the parent entity's `updatedAt`. Read the current value via embed='fields' first if `updatedAt` is being used as a 'last meaningful change' signal. NUMBER quirks: Capsule stores numerics correctly but the read-back via embed=fields returns them as STRINGS (e.g. value=3 reads as '3'); callers comparing values must coerce. TEXT quirks: value='' has the same observable effect as value=null (row removed); empty-string and never-set are indistinguishable."
    • removedInput schema / properties / items / items / properties / organisationId / description
      Removed value: -"For PERSON parties: link to an organisation by id, or `null` to unlink (the person becomes an orphan / standalone record). Discover org IDs via search_parties / filter_parties with type=organisation. For ORGANISATION parties: silently ignored by Capsule's API — organisations don't have a parent organisation in the data model. Empirically verified in v1.6.3 wire-trace; no client-side type guard since the no-op is harmless."
    • removedInput schema / properties / items / items / properties / ownerId / description
      Removed value: -"Pass a user ID to set, or `null` to unassign (verified empirically in v1.6.4 wire-trace — Capsule accepts `owner: null` on PUT /parties/:id for both persons and organisations). Discover IDs via list_users. WARNING: Capsule's PUT on /parties has the same asymmetric owner/team semantic documented in NOTES-ON-CAPSULE-API.md §27 for /kases — setting `owner` while omitting `team` is plausibly clearing-prone. When you supply `ownerId` and omit `teamId`, this connector reads the party's current team and includes it in the PUT body to preserve it across the owner change. Supply `teamId` explicitly to change it."
    • removedInput schema / properties / items / items / properties / phoneNumbers / description
      Removed value: -"APPEND-ONLY: items are merged into the existing list, never replaced. For atomic add/remove/replace use add_party_phone_number and remove_party_phone_number_by_id."
    • removedInput schema / properties / items / items / properties / teamId / description
      Removed value: -"Assign to team ID (discover via list_teams). Pass a team ID to set, or `null` to unassign. Capsule enforces the owner∈team membership constraint — passing a team the current owner doesn't belong to returns 422 'owner is not a member of the team'. Combine `ownerId: null` + `teamId: <T>` in one call to transfer a party to team-ownership with no specific user (verified empirically in v1.6.4 wire-trace; the membership rule doesn't fire when owner is null)."
    • removedInput schema / properties / items / items / properties / websites / description
      Removed value: -"APPEND-ONLY: items are merged into the existing list, never replaced. For atomic add/remove/replace use add_party_website and remove_party_website_by_id."
    • removedInput schema / properties / items / items / properties / websites / items / properties / address / description
      Removed value: -"The website address. A URL when service='URL', or a handle (e.g. '@acmeco') for social services like 'TWITTER', 'INSTAGRAM'. Capsule names this field `address` regardless of service type."
    • removedInput schema / properties / items / items / properties / websites / items / properties / service / description
      Removed value: -"Service type. One of: URL, SKYPE, TWITTER, LINKED_IN, FACEBOOK, XING, FEED, GOOGLE_PLUS, FLICKR, GITHUB, YOUTUBE, INSTAGRAM, PINTEREST, TIKTOK, THREADS, BLUESKY, SNAPCHAT. Defaults to 'URL' if omitted."
  4. Addedv1.7.0
  5. Removedv1.6.2
  6. Addedv1.6.0

TDQS

A4.9/5.0
Behavior5/5

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

The annotations only state that the tool is neither read-only nor destructive, but the description goes much further: it discloses that the connector fans out parallel HTTP requests, the configurable concurrency cap of 5, the exact return shape, and critical partial-failure semantics with no rollback. This is far beyond what the annotations or schema reveal and is essential for correctly handling results.

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

Conciseness5/5

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

Despite being information-dense, every sentence earns its place: purpose, usage scenario, implementation detail, return format, and failure semantics are all covered without repetition. Key facts are front-loaded, with the single-record comparison and usage guidance appearing immediately after the first sentence.

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?

For a batch mutation tool with no output schema, the description is remarkably complete. It specifies the return structure, the possibility of partial failures, the absence of rollback, and the need to inspect per-item results for follow-up. Combined with the fully documented items schema, an agent has all the information required to invoke the tool and interpret its response correctly.

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

Parameters4/5

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

Schema coverage is 100% and the items parameter is thoroughly documented in the schema. The description adds value by pointing out that each item is 'the same shape as update_party,' which lets the agent reuse its knowledge of the single-update tool rather than studying the full nested schema. It also explains the 50-item cap in terms of rate-budget protection, giving rationale beyond the schema's validation rules.

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?

Opens with a precise verb, object, and range: 'Update 1–50 parties in parallel.' It immediately distinguishes itself from update_party by explaining the items-array wrapper and explicitly names the sibling it replaces for bulk writes. An agent can tell this apart from update_party and the other batch_update_* tools without examining the 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?

Explicitly instructs when to use this tool: 'Use this — not N sequential update_party calls — for any homogeneous multi-record write,' with concrete examples like mass owner reassignment and bulk metadata corrections. This provides both the condition and the alternative, leaving no ambiguity about when to prefer batch over sequential calls.

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

Deploy Server

Other Tools