process_recording

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

With no annotations, the description fully discloses critical behavioral traits: it is 'VERY SLOW — can take 15-40 minutes', has shared state constraints ('Only ONE event may be in flight at a time'), and writes to event-details.json. It also warns against retrying and points to cleanup_state for starting over. This is exemplary transparency.

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 compact and front-loaded with the core action, followed by critical operational warnings. Every sentence adds value, and the structure makes the long-running nature and concurrency limit immediately clear.

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 complex, long-running, stateful tool with no output schema and no annotations, the description covers the main inputs, outputs (links written to event-details.json), duration, concurrency, and fallback cleanup. It is sufficient for an agent to invoke and monitor the tool 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?

The input schema provides full descriptions for both parameters (hint_date and hint_title), so schema coverage is 100%. The tool description does not add extra meaning beyond the schema, but the hints are logically connected to finding the recording, so a baseline score of 3 is appropriate.

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 gives a specific, multi-step account: 'find the event recording + transcript on Drive, trim silence, upload to YouTube, and write links back into the event's event-details.json.' It clearly distinguishes this from siblings like draft_event (earlier phase) and cleanup_state (abandonment) by framing it as 'Phase 3'.

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 provides clear usage context: it's a long-running phase that must not be retried while running, and it mentions cleanup_state as the way to abandon a draft. It doesn't explicitly contrast with publish_event or other siblings, but the 'Phase 3' label and concurrency warning give practical guidance.

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