Skip to main content
Glama
Sign In
TimWongUp

AgentNave

by TimWongUp
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Cancel a task or round

cancel
DestructiveIdempotent

Stop a running task or round and return its halted or already-finished result while preserving published answers and keeping undecided answers private.

Instructions

Stop a task or round; return its cancelled or already-finished result. Running seats become absent, unstarted seats skip, published answers stay and undecided answers stay private. CLI side effects are not undone.

Input Schema

NameRequiredDescriptionDefault
idYesAn invocation_id from start_agent or a round_id.

Output Schema

NameRequiredDescriptionDefault
roundNo
invocationNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.65.0
    • changedOutput schema / $defs / InvocationPayload / required
      Previous value: -[
-  "invocation_id",
-  "status",
-  "reason",
-  "elapsed_ms"
-]New value: +[
+  "invocation_id",
+  "status",
+  "reason"
+]
  2. Changed3 schema fields changedv0.53.1
    • addedOutput schema / $defs / InvocationPayload / properties / warnings
      Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "title": "Warnings",
+  "type": "array"
+}
    • addedOutput schema / $defs / SeatRunPayload / properties / output_returned
      Added value: +{
+  "title": "Output Returned",
+  "type": "boolean"
+}
    • addedOutput schema / $defs / SeatRunPayload / properties / warnings
      Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "title": "Warnings",
+  "type": "array"
+}
  3. Changed1 schema field changedv0.49.0
    • addedInput schema / additionalProperties
      Added value: +false
  4. Addedv0.35.0

TDQS

A4.2/5.0
Behavior5/5

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

Even though annotations already declare destructiveHint=true and idempotentHint=true, the description adds substantive semantics beyond them: what happens to running seats (become absent), unstarted seats (skip), published answers (retained) versus undecided answers (stay private), and that CLI side effects are not undone. That is exactly the 'what gets destroyed and what survives' context an agent needs before invoking a destructive tool.

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

Conciseness5/5

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

Front-loaded with the action, then two compact clauses covering return shape and state outcomes. Every clause carries information an agent cannot get from the annotations or schema; nothing is redundant padding.

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?

Output schema exists and annotations cover safety/idempotency, so the description needn't explain return values; it nonetheless covers the state transitions well. The only gap is operational context — no note on authorization requirements or on calling this after an invocation has already been reaped by another actor.

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% and the single parameter is fully documented ('An invocation_id from start_agent or a round_id'). The description adds no meaning beyond the schema — it never mentions the id or its two accepted forms — so the baseline 3 applies.

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?

States a specific verb and resource — 'Stop a task or round' — and immediately adds the return nuance ('cancelled or already-finished result'). No sibling (start_agent, run_round, wait, decide_answers) performs a stop/cancel action, so the tool is unambiguously distinguishable from the listed alternatives.

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?

Usage is implied rather than stated: an agent can infer it should call this when it wants to halt an in-flight invocation or round. There is no explicit when-not-to-use guidance, no mention of which sibling to prefer for graceful termination (e.g. handover), and no statement of the preconditions on the id.

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

Deploy Server

Other Tools