Start Agent Run

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, so the agent knows this is a mutating operation. The description adds that it is 'paid' and 'permissions enforced', but does not elaborate on what constitutes destruction (e.g., credit consumption, state changes) or other behavioral nuances beyond what annotations provide.

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 description is a single sentence with no wasted words. It is front-loaded with the core action and resource, achieving maximum conciseness. Every word contributes meaning.

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 the tool's complexity (13 parameters, no output schema, openWorldHint), the description is highly insufficient. It does not explain how the run progresses, what the return value is, how to handle billing errors, or how to integrate with sibling tools like glitch_wait_for_agent_run. Critical behavioral context 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?

The description provides no additional explanation for the 13 parameters. Schema coverage is only 46%, meaning many parameters lack inline descriptions, and the tool description does not compensate. For example, 'run_type' and 'trigger_source' are not explained in the description, leaving agents without guidance on their usage.

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 clearly states the action ('Start a paid Glitch Agent run'), the resource ('for a title'), and includes context ('Subscription and title permissions are enforced by Glitch'). It effectively distinguishes from sibling tools like glitch_answer_guidance or glitch_get_agent_run by specifying the initiation of a run.

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?

The description mentions that the run is paid and that permissions are enforced, but it does not provide explicit guidance on when to use this tool versus alternatives (e.g., when to start a run vs. wait for it). The usage context is implied but not clearly delineated, leaving room for ambiguity.

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