underway

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the agent knows this is a safe, open-ended read. The description adds valuable behavioral context: the tool returns exactly one question per call, follows the interview stages, and on completion returns 'done', a summary, a closing line, and an opening link. This is helpful beyond annotations, though it doesn't discuss rate limits or multi-turn persistence explicitly.

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 two dense sentences that front-load the core action and the completion outcome, then clearly state usage and the alternative. It is efficient with no wasted words, though the second sentence could be slightly shortened.

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 a single-parameter tool with full schema coverage, an output schema (so return values needn't be explained), and annotations covering safety/openness, the description provides complete context: what it does, how it progresses across calls, what completion returns, and when to use it versus the sibling. An agent has everything needed to invoke it correctly.

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% and the parameter is already documented as the ordered message history. The description adds meaning by specifying that the returned question follows up on what the user said, implying the agent must pass the full conversation and that the function maintains state via messages. This is a slight improvement over the schema baseline.

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?

States a specific verb (runs an interview) and resource (debrief with a founder), and names the exact stage progression (start, work, problem, resolution, forward). It clearly distinguishes itself from the sibling underway_set_up_recording by contrasting 'talk through their day now' vs 'set up recording'.

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 explicit when-to-use guidance ('when a founder wants to talk through their day now, in this chat') and when-to-use-alternative guidance ('If they already know they want to film and only want it set up, use underway_set_up_recording instead'). This is a clear decision boundary.

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?

Annotations declare readOnlyHint=false but destructiveHint=false and openWorldHint=true; the description reconciles that tension by stating plainly that it 'records nothing and runs no interview,' which is non-obvious and prevents an agent from assuming a recording starts. It also discloses the return payload (a one-line description plus a deep link), though the output schema already covers returns, so it stops short of a 5.

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?

Front-loaded with the action, then the return, then the behavioral caveat, then the routing rule — a sensible order with no filler. It runs slightly long, and 'It records nothing and runs no interview' partially duplicates the same point twice, keeping it from a 5.

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 no-required-parameter setup tool with a full output schema and complete enum documentation, the description supplies everything an agent needs: what it configures, that it performs no recording or interview, what it returns, and when to prefer the sibling. Nothing material is left to inference.

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% with rich enum descriptions for clock, frame, and format, so the schema already carries the parameter meaning. The description's recital of 'how long, camera or podcast, portrait or landscape, questions or just talking' restates those fields rather than adding format, default, or interaction detail beyond them.

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?

States a specific verb and resource ('Prepares a recording in Underway') and enumerates the decision inputs it consumes (length, camera vs podcast, orientation, questions, topic). It explicitly names the sibling underway_debrief as a different tool for a different intent, so an agent can route without opening either 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?

Gives both the use condition ('when the founder wants to film in Underway and has said how') and the exclusion with its alternative ('to talk through their day here instead, use underway_debrief'). This is explicit when/when-not/alternative guidance.

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