add_comment_tool

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

With no annotations present, the description carries the full burden of behavioral disclosure. It reveals that times are timeline seconds rather than source-media time, that empty track_ids means session-wide, that the operation is undoable, and that passing edit_decision_id opens the single Ask thread. It doesn't cover every side effect, but it provides substantial behavior beyond the schema.

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 well-structured and front-loaded: purpose appears first, followed by key temporal semantics, parameter clarifications, undoability, and the special edit_decision_id behavior. Every sentence carries useful information; there is no filler or tautology.

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 8 parameters, no annotations, and a rich sibling set, the description is notably complete. It covers timing, anchoring, optional parameters, session-wide behavior, undoability, and the reply-tool boundary. Minor gaps include lack of contrast with add_comment_action_tool and no detail on how 'span' relates to timeline_end, but these are not critical for basic correct invocation.

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 0%, so the description must compensate. It explains timeline_start/end semantics, clarifies that track_ids_json and action_texts_json are JSON arrays of optional strings, and describes edit_decision_id's special behavior. It leaves body, author, and project_path unexplained, but those are relatively self-evident from their names and required status.

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 tool's function: 'Add a timeline review comment (instant or span)' – a specific verb with a defined resource. It differentiates from add_comment_reply_tool by noting that later notes must use the reply tool, but it does not explicitly distinguish itself from add_comment_action_tool among the siblings.

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 gives practical usage direction: use search_transcript_tool's timeline_start/end when anchoring to dialogue, pass edit_decision_id for a specific pending-cut Ask thread, and use add_comment_reply_tool for later notes. It lacks explicit 'when not to use' guidance regarding other sibling comment tools, but the context is useful and actionable.

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