mesh_lobby_transcript

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

With no annotations and no output schema, the description carries the full burden and it does so thoroughly: it discloses a local SQLite read that never blocks and never makes a round trip, the transcript persists after watching stops, and the data is only ever that which arrived after the watch started. That gives the agent deep practical knowledge of latency, side effects, and data vintage.

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 the core read action and local provenance, then the two modes, then the caveats, and each sentence earns its place. It loses one point for long, nested parentheses in the topic sentence that slow parsing and for some overlap with the topic filter the scheme already states.

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 surface is small (2 optional parameters, no output schema) and the description covers the main return behavior: the fallback topic list plus interleaved facts when omitted, raw conversation when given. It lacks only the exact canonical shape of a raw transcript row, and that is securely left open given the schema's definitions.

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%, so baseline is 3, but the text adds real value beyond the scheme: concrete example topic values (agents.lobby, a room_topic) and the outcome of the omission — an interleaved stream plus the distinct-topic list for narrowing. The limit parameter already self-describes in the scheme, so no additional wording is needed.

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's opening verb resets, 'Read what mesh_observe_lobby has recorded', names the specific resource and provenance in one short clause, so an agent instantly knows this reads an observed transcript rather than a broadcast, inbox, or store. The two modes (every topic vs a single conversation) are stated distinctly and mesh_read_inbox is named as the sibling it is not.

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 explicit when-to guidance: omit the topic for everything interleaved by arrival time, or pass agents.lobby/a room_topic for a narrow raw read, and it points to mesh_read_inbox as the threaded alternative when you want rooms you are actually in. It also states the strongest exclusion — 'Never retroactive' — which prevents the agent from using this for history that predates the watch.

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