agent_task

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

Documents key defaults (maxSteps=50, maxActionsPerStep=100) and async behavior. However, with no annotations provided, it omits critical behavioral context: return values (taskId vs results), default mutability (can modify files unless readOnly=true), and what subsystems/actions the agent can invoke.

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?

Extremely concise and front-loaded (purpose first, then guidance). Three fragments efficiently convey distinct concepts. However, brevity underserves the tool's high complexity (15+ effective parameters).

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?

Given high complexity (nested options object, numerous controls) and absence of annotations or output schema, the description covers basics but should clarify return behavior, error handling, and safety boundaries for a powerful agent tool.

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?

Adds meaningful semantic guidance beyond the schema: explicitly mapping readOnly to 'analysis' use case and async to 'long tasks'. Also surfaces default values for tuning parameters that the schema only describes mechanically.

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?

Clear verb ('runner') and resource ('multi-step task'), establishing it as the general-purpose autonomous agent. Distinguishes from single-purpose siblings like search or analyze_file, though doesn't explicitly differentiate from similar orchestration tools.

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?

Provides implicit guidance via option hints ('Use readOnly for analysis', 'use async for long tasks'), but lacks explicit criteria for when to select this tool over siblings like orchestration, code_helper, or mcp_plan_implementation.

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