underway

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

Beyond standard hints, the description details the complex flow: returning specific question types (start, work, problem, etc.), transitioning to a 'done' state, generating a summary, providing a closing line, and producing a load link. This outlines the entire operational lifecycle of the tool.

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 information is highly dense, well-structured, and front-loaded. It delivers the 'what,' the 'how,' and the 'when/when-not' in a minimal number of words.

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 stateful, multi-turn conversational tool, this description is complete. It explains the iterative nature, the final output components (summary, link), and the scope of the operation, leaving no execution gaps.

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?

While the schema defines the structure, the description provides critical semantics for the input: it dictates that the `messages` array must contain only the interview history, clearly defining the roles and the order of input history, which is essential for a stateful interactive tool.

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 purpose is clear: running a short, iterative interview (debrief). It distinguishes itself by specifying the outcome—a sequence of questions or the final 'done' state—and contrasts itself directly with the sibling tool.

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 provides explicit instructions on when to use it ('talk through their day now, in this chat') and when to use the alternative ('use underway_set_up_recording instead'). This prevents agent misuse.

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

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

With annotations already declaring readOnly=false, openWorld=true, and destructive=false, the description adds meaningful behavioral context: it returns a one-line setup description and a ready-to-film link, opens Underway configured that way, and explicitly 'records nothing and runs no interview.' This prevents an agent from mistaking it for an actual recording or interview tool.

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 front-loaded with purpose, then return behavior, then explicit negative behavior, then usage guidance. Every sentence contributes distinct information with no repetition or filler.

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?

The tool has an output schema and fully described parameters, and the description still covers the important behavioral boundary: it sets up rather than records. It also names the sibling alternative, leaving no significant gap for an agent deciding how to call it.

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 description coverage is 100% and all five parameters are already well documented in the input schema. The description maps the choices in natural language ('how long, camera or podcast, portrait or landscape, questions or just talking') but adds no syntax, defaults, or constraints beyond what the schema provides.

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: 'Prepares a recording in Underway' from the founder's choices. It names the setup dimensions and distinguishes the tool from underway_debrief, so an agent can identify it without opening the schema.

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 gives an explicit use condition: 'Use it when the founder wants to film in Underway and has said how.' It also names the alternative and when to choose it: 'to talk through their day here instead, use underway_debrief.'

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