Skip to main content
Glama
soil-dev

capsulemcp

update_opportunity

Update any field on an existing opportunity, including reassigning party, milestone, owner, or team. Preserve or clear owner/team with null values.

Instructions

Update fields on an existing opportunity, including the parent-reference field partyId to reassign the opp to a different primary party. ownerId and teamId both accept null to unassign (verified empirically in v1.6.5 wire-trace — brings update_opportunity into parity with update_party and update_project). The combination {ownerId: null, teamId: <id>} puts an opportunity into 'team-owned, no specific user' state, matching the pattern available on parties and projects. Only the fields you provide are changed. Closed (Won/Lost) opportunities ARE editable — Capsule does not enforce closed-record immutability, so value, description, etc. can be changed on a Won opp without warning. If the workflow needs historical revenue numbers to be stable, enforce that caller-side. Capsule requires every opportunity to have a party — passing partyId: null is rejected with 422 'party is required' (Unlike update_task.partyId which IS nullable — tasks can be orphaned in Capsule's model).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNo
nameNo
partyIdNoReassign the opportunity to a different primary party. Capsule requires every opportunity to have a party — passing `null` is rejected with 422 'party is required' (use Capsule's web UI if you need to dissolve the link entirely). Discover ids via search_parties / filter_parties. No defensive read-modify-write needed: this connector verified empirically (v1.6.3 wire-trace) that `party` is a standalone PUT field on /opportunities and does not interact with the asymmetric owner/team semantic from NOTES-ON-CAPSULE-API.md §27. NOTE: parent-ref nullability differs by entity — `update_task.partyId` IS nullable (orphan task), but opportunities and projects must always have a parent party. The same applies to `update_project.partyId`.
milestoneIdNoMove the opportunity to this milestone. Side effects depend on the target: closing milestones (Won/Lost) auto-set `closedOn` to today and `probability` to the milestone default (100/0), preserving `lastOpenMilestone` as the previous open stage; moving back to an open milestone clears `closedOn` and re-applies the milestone's default probability (Won/Lost is reversible — no separate reopen tool). WARNING: Capsule does NOT validate that the new milestone belongs to the opportunity's current pipeline. Passing a milestoneId from a different pipeline silently relocates the opportunity across pipelines, and `lastOpenMilestone` may then reference a milestone in the previous pipeline. Verify against the opportunity's current pipeline (read the opp first, list its pipeline's milestones via list_milestones) before passing a cross-pipeline id. NOTE: changing `milestoneId` can fire **pipeline / milestone-reached automations** that mutate `owner` / `team` on the destination milestone (same shape as `create_opportunity` — see its `milestoneId` description for the owner-clearing automation caveat). If a milestone-change-and-owner-set in the same call lands with `owner: null`, follow up with a second `update_opportunity` (or `batch_update_opportunity`) carrying both `ownerId` and `teamId` — milestone-reached triggers only fire on the transition, so a subsequent PUT preserves your values.
descriptionNo
valueNo
expectedCloseOnNo
probabilityNoWin probability 0–100. On an open milestone this overrides the milestone's default probability. CANNOT be set in the same call as a closing milestone (Won/Lost) — Capsule processes the milestone change first, the opportunity becomes closed, then the probability update is rejected as edit-on-closed-opp with 422 'probability can be updated only for open opportunity'. To close an opportunity, leave probability out of the call: it auto-snaps to 100% (Won) or 0% (Lost).
lostReasonIdNoReason the opportunity was lost. Only meaningful when transitioning to a Lost milestone — Capsule silently drops it for other milestones. Without this set, a connector-driven Lost-close leaves `lostReason: null`. Discover IDs via list_lostreasons.
ownerIdNoReassign owner: pass a user ID to set, or `null` to unassign (verified empirically in v1.6.5 wire-trace — Capsule accepts `owner: null` on PUT /opportunities/:id, mirroring the v1.6.4 finding on /parties; brings update_opportunity into parity with update_party and update_project). When you supply `ownerId` and omit `teamId`, the connector fetches the opportunity's current team and includes it in the PUT body to preserve it across the owner change. Without this defensive read, Capsule's PUT would clear the existing team (see NOTES-ON-CAPSULE-API.md §27 — same asymmetric semantic as /kases). Supply `teamId` explicitly on the same call to change the team instead. Combine `ownerId: null` + `teamId: <T>` in one call to transfer an opportunity to team-ownership with no specific user (verified empirically in v1.6.5; the owner-clears-team semantic doesn't fire when owner is being cleared to null).
teamIdNoReassign team: pass a team ID (discover via list_teams) to set, or `null` to unassign. Capsule preserves the existing owner across a team change (server-side), so `update_opportunity { teamId }` alone is safe — the owner is carried through. Owner must be a member of the new team or Capsule returns 422 'owner is not a member of the team'. Independent from `ownerId` — setting `teamId` does NOT clear the owner.
fieldsNoSet 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_opportunity with embed='fields'.
Behavior5/5

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

The description fully discloses behavioral traits beyond annotations. It reveals that closed opportunities can be edited, that Capsule does not validate pipeline membership for milestones, that milestone changes can trigger automations affecting owner/team, and the nuances of nullability across fields. Empirical verifications are cited. No contradiction with annotations (readOnlyHint=false, destructiveHint=false).

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

Conciseness4/5

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

The description is verbose but well-structured. It opens with the core purpose, then delves into parameter-specific details. Every sentence adds value, and critical caveats are front-loaded. However, it could be slightly more concise; for instance, the empirical verification details could be summarized. Still, it earns high marks for clarity and organization.

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?

Given the tool's complexity (12 parameters, nested objects, no output schema), the description is remarkably complete. It covers all fields, edge cases (nullability, cross-pipeline milestones), empirical findings, interactions between parameters, and even references sibling tools for comparison. Every aspect that an agent might need to safely invoke the tool is addressed.

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

Parameters5/5

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

Despite only 58% schema description coverage, the tool description compensates with rich parameter semantics. For every parameter, it adds meaning beyond the schema: e.g., partyId nullability differences from tasks, milestoneId side effects (automations, cross-pipeline relocation), probability cannot be set with closing milestones, ownerId/teamId interactions and defensive read behavior, custom field quirks (BOOLEAN two-state, numeric read-back as strings). This is highly informative.

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?

The description clearly states the tool's purpose: 'Update fields on an existing opportunity'. It specifies the verb (update), resource (opportunity), and scope (fields, including parent-reference, owner, team, etc.). It distinguishes from siblings like create_opportunity, update_party, and update_project by highlighting unique behaviors (e.g., closed-opp editability, owner/team nullability).

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?

The description provides extensive guidance on when to use this tool and when not, including alternatives. It explains that closed opportunities ARE editable, recommends caller-side enforcement for revenue stability. It details how to handle owner/team reassignment (including null values), milestone changes with cross-pipeline warnings, and the interaction between probability and closing milestones. It also advises reading current state before changes.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/soil-dev/capsulemcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server