Skip to main content
Glama

scope_create

Create a named retrieval scope with registry-validated allow-lists across source databases, domains, and semantic or native codes to narrow queries to matching indicators, cutting retrieval cost and noise.

Instructions

Create a named retrieval scope.

rules: allow-lists over the registry dimensions — {source_dbs: [...], domains: [...], semantic_codes: [...], native_codes: [...]} (every list optional; a scope with no allow-lists is rejected). Allow-list values are validated against the live registry_entries/concepts tables: a scope matching nothing known is rejected; the number of matched indicators is returned. unscoped is reserved. Scope is a precision/cost tool, not a permission wall.

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": {
      "name": "<name>",
      "rules": "<rules>"
    },
    "name": "scope_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYes
rulesYes
descriptionNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare the mutation profile (readOnly=false, destructive=false, idempotent=false), so the bar is lower. The description adds real context — validation against live registry tables, rejection of empty/unmatched scopes, and that the matched indicator count is returned — but says nothing about duplicate-name behavior or what happens on re-creation, leaving the idempotent=false hint unexplained.

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 action, then structured rules and caveats; no filler sentences. The parenthetical and validation clauses are dense but each carries information the schema lacks.

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?

Rich enough for a nested-object mutation tool: rules shape, validation semantics, reserved name, and return signal are all covered, and an output schema exists so return values need no elaboration. Only the `description` field and duplicate-name/idempotency behavior are left unaddressed.

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?

With 0% schema coverage the description carries the full burden and largely does: it enumerates the four allow-list keys inside `rules`, states each list is optional but at least one is required, and notes `unscoped` is reserved. The `description` parameter is never mentioned, which is the one remaining gap.

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 specific verb+resource ("Create a named retrieval scope") and immediately frames it conceptually as "a precision/cost tool, not a permission wall," which distinguishes it from the policy_create sibling without naming it.

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?

Gives useful preconditions: allow-lists must be non-empty, values are validated against the live registry_entries/concepts tables, and an unmatched scope is rejected. The "not a permission wall" line steers agents toward the policy family for access control, but no alternative tool is named explicitly and no when-not-to-call statement is given.

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