Skip to main content
Glama

Update account (CRM)

crm_update_account
Destructive

Correct or deepen the account narrative. Only the fields you pass change. Provenance survives updates (CRM-9): why_them and source_url can be corrected, never blanked. Status moves have their own command, with its own rules.

PARKING IS NOT A STATUS MOVE (CRM-18). status is a judgement about where a pursuit sits; parking is a fact about what happened to it — both intake routes dead, the sponsor left, a reorganisation in flight. An account parked at researching is still at researching, and says why nobody is spending time on it. Parking needs a reason, is reversible with park="", and takes the account out of the worklists until it comes back. Effects: account narrative updated; account parked or unparked, with the reason kept.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "account_id": "<account_id>"
    },
    "name": "crm_update_account"
  }
}

Input Schema

NameRequiredDescriptionDefault
hookNoThe one-sentence opener you would actually use.
nameNoRename, if the company did.
parkNoWhy this account should be left alone, as a fact about what happened. Empty string unparks it. Read by whoever considers reopening it, so "both intake routes dead: form errors, research@ bounced 11 Sep" is useful and "not worth it" is not.
tierNo1–3. Tier semantics are yours; 1 usually means "worth a hand-written approach".
verticalNoIndustry vertical, your taxonomy.
why_themNoCorrecting, not blanking (CRM-9).
account_idYesThe account. An existing account id.
owner_noteNoWorking notes.
source_urlNoCorrecting, not blanking (CRM-9).
trigger_eventNoWhat changed that makes now the moment. A fact, with the source in source_url.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations it discloses several non-obvious behaviors: provenance fields (why_them, source_url) survive updates and can be corrected but never blanked, parking requires a reason that is retained, parking is reversible via an empty string, and parked accounts drop out of worklists until unparked. These effects materially change how an agent should call a tool flagged destructiveHint=true and non-idempotent.

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?

Front-loaded with the core mutation contract, then the parking distinction, then the effects list — a sensible order. The parking paragraph is long and leans on internal rule codes (CRM-9, CRM-18), but every sentence carries information an agent needs to avoid mishandling `park`.

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

Completeness4/5

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

Ten parameters with only account_id required, no output schema, and destructive semantics — the description covers the mutation contract, the two governed fields, the parking side effect, and the resulting state changes. It doesn't describe what a successful call returns, but with no output schema that gap is minor.

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%, so baseline would be 3, but the description adds conceptual meaning the schema doesn't: it reframes `park` as a recorded fact with a retention rule and distinguishes it from `status` entirely, which prevents the most likely misuse of that parameter. The remaining parameters (tier, vertical, hook, owner_note) are left to the schema.

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

Purpose4/5

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

The description states a specific verb and resource ('Correct or deepen the account narrative') and pins down partial-update semantics with 'Only the fields you pass change.' It also carves out scope against the status workflow ('Status moves have their own command'), though it does not name crm_set_account_status or distinguish itself from crm_add_account directly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

It gives an explicit when-to-use rule for the tricky field: parking is for facts about what happened, not for judgements about pursuit stage, and it names the sibling alternative implicitly by saying status moves live elsewhere. It also covers the reverse operation (park="" unparks). What's missing is any guidance on when to update the narrative fields versus using the add/status/promote siblings.

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.