run_prepared_task

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does state that the tool does not route or switch models, which is a behavioral trait, but it omits other critical behaviors such as whether it blocks, whether it has side effects on the plan state, whether it requires prior approval (implied by 'approved plan' but not explicit), or whether it is idempotent. The lack of any annotation coverage makes this a significant gap.

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 concise, consisting of two short sentences with no filler or redundant information. The key action and the critical exclusion are front-loaded, making it easy to parse quickly. However, the extreme brevity comes at the cost of essential information, so while it is well-structured, it is not optimally complete.

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 tool with three parameters, no annotations, and a large set of siblings, this description is severely incomplete. It does not explain what 'provider work' entails, what the expected output is (even though an output schema exists, the description does not reference it), or how this tool fits into the broader pipeline workflow. The single differentiator (no routing/switching) is insufficient to guide an agent in correctly invoking this tool, especially given the ambiguity of the parameters like response_detail and next_tier_suggestion.

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 schema description coverage is 0%, meaning the description provides no explanation of any parameters. The tool has three parameters (plan_token required, response_detail and next_tier_suggestion optional), and the description does not mention any of them. With zero coverage, the description must compensate for the schema's lack of descriptive text, but it does not, leaving the agent without any semantic understanding of the parameters beyond their names.

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 action: 'Begin provider work for one approved plan.' This is a clear verb+resource combination that conveys the tool's core function. The addition of 'Never routes or switches models' provides a differentiating constraint that helps distinguish it from sibling tools like route_task and switch-related tools. However, the term 'provider work' is somewhat vague and could be more explicit about what the work entails.

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 only offers a negative constraint ('Never routes or switches models') but does not provide positive guidance on when to use this tool versus alternatives like prepare_task, approve_preflight, or confirm_and_run. There is no explicit statement of prerequisites, such as requiring an approved plan, nor any indication of when not to use it beyond the routing/switch exclusion. This leaves the agent to infer the usage context.

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