Skip to main content
Glama
Sign In

TaScan

by io.github.snowbikemike
OverviewDiscussionsAdmin

tascan_delegate_to_agent

Mint a time-limited, NARROWER child API key (POST /delegations, roadmap #11) — only read/write scopes may be requested; full, agent:dispatch, agent:dispatch:code, device:admin, delegate and webhooks:manage are always refused by name (I-6). TTL defaults to 1 hour (3600s), clamps to [60 seconds, 24 hours], and clamps further to THIS key's own expiry if it has one — a delegated key can never outlive its grantor. The child's tier is always a SUBSET of this key's own effective tier, never wider or lateral. Requires the delegate permission (owner-only to grant, requires full). The returned raw key is shown to you exactly ONCE — it is never stored server-side and cannot be retrieved again (I-10). Revoking this key (or any ancestor) cascades immediately to every key it delegated.

Input Schema

NameRequiredDescriptionDefault
roleNoThe agent’s job on the project: builder, researcher, reviewer, panelist, ...
modelNoThe model the agent runs on, e.g. claude-sonnet-5-5.
scopesYesScopes to request for the child key — read and/or write only.
vendorNoThe model vendor (defaults to this key’s own vendor).
agent_idNoStable agent id used in receipts and the agent registry.
ttl_secondsNoHow long the child key lives, in seconds (default 3600 = 1h; clamped to [60, 86400] and to this key's own expiry).
display_nameNoReadable id for the agent, e.g. "LT-ZOOS-RSCH-02 · Zoos · Researcher 02".
resource_constraintsNoOptional project sandbox: { "project_ids": ["<project uuid>", ...] }. Enforced on every call (migration 249): the child reaches only those projects. Must be a subset of this key’s own projects when this key is itself project-limited; omitted, the child inherits this key’s projects.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / agent_id
      Added value: +{
+  "description": "Stable agent id used in receipts and the agent registry.",
+  "type": "string"
+}
    • addedInput schema / properties / display_name
      Added value: +{
+  "description": "Readable id for the agent, e.g. \"LT-ZOOS-RSCH-02 · Zoos · Researcher 02\".",
+  "type": "string"
+}
    • addedInput schema / properties / model
      Added value: +{
+  "description": "The model the agent runs on, e.g. claude-sonnet-5-5.",
+  "type": "string"
+}
    • changedInput schema / properties / resource_constraints / description
      Previous value: -"Optional free-form narrowing (e.g. project/list ids) recorded on the child key as metadata."New value: +"Optional project sandbox: { \"project_ids\": [\"<project uuid>\", ...] }. Enforced on every call (migration 249): the child reaches only those projects. Must be a subset of this key’s own projects when this key is itself project-limited; omitted, the child inherits this key’s projects."
    • addedInput schema / properties / role
      Added value: +{
+  "description": "The agent’s job on the project: builder, researcher, reviewer, panelist, ...",
+  "type": "string"
+}
    • addedInput schema / properties / vendor
      Added value: +{
+  "description": "The model vendor (defaults to this key’s own vendor).",
+  "enum": [
+    "anthropic",
+    "openai",
+    "gemini"
+  ],
+  "type": "string"
+}
  2. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only supply generic hints (readOnlyHint=false, destructiveHint=false, idempotentHint=false); the description goes far beyond, disclosing TTL defaults and dual clamping (range and grantor expiry), tier subsetting rules, one-time-only raw key display with no server storage (I-10), and cascade revocation on ancestor revoke. This is exactly the behavioral context annotations can't carry.

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 key action is front-loaded and every clause carries substantive policy (scope refusals, TTL clamps, tier subset, one-time key, cascade revoke). It is dense and studded with internal references (I-6, I-10, roadmap #11, migration 249) that add noise for an agent, keeping it from a 5.

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?

For a non-idempotent, open-world=false mutation with 8 params and no output schema, the description covers the critical unknowns: the raw key is returned exactly once and cannot be retrieved again, plus lifecycle and inheritance behavior. It stops short of describing any other response shape, but nothing essential for correct invocation is missing.

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 the baseline is 3, but the description adds real semantic context: the scopes array is constrained to read/write with everything else refused by name, and resource_constraints is described as inheriting the parent's projects when omitted. Minor added value beyond the schema's own descriptions.

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+resource+qualifier: 'Mint a time-limited, NARROWER child API key'. This clearly separates it from siblings like tascan_revoke_delegation, tascan_list_delegations, and tascan_dispatch_to_agent, and the API route (POST /delegations) pins the operation.

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?

States the precondition (requires the delegate permission, owner-only to grant, requires full) and enumerates which scopes are always refused by name (full, agent:dispatch, device:admin, delegate, webhooks:manage), which tells the agent when this tool is applicable. It does not explicitly contrast with a named alternative sibling, so it stops short of a 5.

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

All TaScan toolsInspect
Try in Browser
Pay for results, not tokens.Fund a bounty. Let AI agents compete and collaborate to solve your problems.agentbounties.appAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources