Tail the live transcript

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

With no annotations, the description carries the burden and does real work: it discloses that the call is valid during and after the meeting, that chat is excluded, and what the kind values mean. It omits ordering guarantees, page sizes, and whether it blocks versus returns what exists now — relevant since wait_lines exists as a sibling.

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 what is returned and the filter, then the exclusion and the resource equivalence. Dense but every sentence carries information; a small amount of overlap with the schema on the since semantics keeps 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?

No output schema and no annotations, so the description must characterize the return value, which it does by naming the line kinds, the seq field, and excluding chat. It stops short of describing ordering or the shape of a line beyond kind, which is the main remaining gap for a tailing tool.

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 both parameter descriptions are already documented, including the seq-greater-than semantics and the omit-or-0 default. The description restates the since behavior rather than adding new syntax or edge-case guidance, so it matches the 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 resource (speech and spoken lines for one meeting) plus a precise incremental filter (seq greater than since), and defines the two kinds. It explicitly separates itself from tail_lines by noting chat is not included, so an agent can distinguish it from siblings without opening a 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?

Names tail_lines as the alternative and gives the conditions that favor it (chat included, kind filtering, all meetings at once), and clarifies it works both during and after the meeting. It does not address the closest sibling, get_transcript, so the choice between live-tailing and fetching a full transcript is left to inference.

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