Skip to main content
Glama

Resolve gap

crm_resolve_gap
Destructive

Turn a gap into a named contact — with full provenance. The only way a gap becomes named (CRM-2), and it demands the same provenance as a fresh contact — the gap does not lower the bar. The gap_note stays on the row: what we did not know is part of how we came to know it. Effects: contact gap -> named.

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": {
      "contact_id": "<contact_id>",
      "name": "<name>",
      "source": "<source>"
    },
    "name": "crm_resolve_gap"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesThe person.
emailNoAs publicly listed or personally shared, if the source includes one.
phoneNoSame rule as email.
titleNoTheir title, as the source states it.
sourceYesWhere the name comes from (CRM-1).
contact_idYesThe gap row, e.g. P-0002.
linkedin_urlNoThe person's public LinkedIn profile URL, if the source includes one.
confidence_noteNoHow sure, and of what.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds real behavioral context beyond them: the provenance bar is not lowered for gaps, and critically 'The gap_note stays on the row' tells the agent what is preserved rather than overwritten. What it does not disclose is why the operation is destructive — whether the gap row is consumed, replaced, or duplicated — nor what happens on a re-run or a name collision.

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?

The action is front-loaded and the 'Effects:' line is an efficient summary. But the second sentence largely restates the first ('The only way a gap becomes named'), and the aphorism about what we did not know costs words without adding callable guidance.

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

Completeness3/5

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

For an 8-parameter destructive mutation with no output schema, the definition covers the core state transition and the retention of gap_note. It leaves gaps an agent would care about: there is no return-value description, no error or duplicate-handling behavior, and no indication of whether the operation can be undone.

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% across all 8 parameters, so the schema already carries the per-field semantics and the baseline of 3 applies. The description reinforces the provenance requirement ('demands the same provenance as a fresh contact', 'source ... CRM-1'), which signals that provenance fields are mandatory in spirit, but adds no format, validation, or fallback details for individual parameters.

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?

States a concrete verb and transformation: 'Turn a gap into a named contact', with a compact 'Effects: contact gap -> named' restatement that makes the state change unambiguous. The phrase 'The only way a gap becomes named (CRM-2)' differentiates it from generic contact tools like crm_add_contact or crm_update_contact, though the abstract term 'gap' is never grounded beyond the contact_id example 'P-0002'.

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

Usage Guidelines3/5

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

The claim 'The only way a gap becomes named' functions as an exclusivity signal, telling the agent this is the route for gaps rather than plain contact creation. However, there is no explicit when-not-to-use, no prerequisite stating a gap row must already exist, and no guidance on what to do if the person already exists as a contact — usage is implied rather than spelled out.

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.