Agent Task Management

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

Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description discloses that mutations persist to the Novel and are audited, that list/get are read-only, that the most recent mutation is revertible via manage_history undo, and that terminal tasks are immutable. These are non-obvious behavioral traits that an agent could not derive from the annotation flags alone.

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

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

The opening sentence front-loads the core purpose, followed by mutability/audit facts, the undo path, and a compact when/when-not block. Every sentence carries distinct information with no filler, despite covering a large action surface.

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

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

For a 7-parameter mutation tool with an output schema present, the description covers purpose, mutability, audit/persistence, undo, immutability constraints, and sibling routing. Return values need not be explained because the output schema exists, so nothing an agent needs to invoke this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

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 lifecycle meaning to the action parameter by glossing how each value is used ('logging an action (advance)', 'settling it (complete/fail/cancel)'). This clarifies the operational intent of the enum beyond the bare schema listing, though it does not add syntax or format detail for the other parameters.

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

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

The description states a specific verb and resource ('Manage durable NPC/agent tasks and their action lifecycle') and enumerates the concrete operations (create, start, advance, complete, fail, cancel, list, get). It is clearly distinguishable from siblings like manage_scene, manage_npc, and manage_history, which are each named with a disambiguating condition.

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

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

It has explicit 'Use when' and 'Do NOT use when' sections, and routes the agent to alternatives with the exact call syntax: manage_history (action: undo), manage_scene (action: oracle), manage_npc. Both the positive triggers and the exclusions are spelled out, leaving nothing to inference.

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