mesh_lobby_transcript

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

With no annotations, the description carries the full burden and does so thoroughly: local SQLite read, never blocks, never makes a mesh round trip, non-retroactive coverage, persistent like mesh_agents' roster. It even documents the `dropped`/`dropped_by_topic` semantics, the 256-event inbox discard behavior, and the macula-mcp 0.35.0 version qualifier — behavioral detail far beyond a mere restatement.

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 core purpose and the read-only/local nature before the detail. The final `dropped` explanation is long and dense, but since there is no output schema it earns its place as return-value documentation rather than padding.

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 exists, so the description must explain return values — and it does, covering the topic list, the raw transcript, and both `dropped` and `dropped_by_topic`. Combined with the mutation-free/caching behavior and the non-retroactive constraint, nothing an agent needs to call this correctly is missing.

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 the baseline is 3, but the description adds real meaning: it explains what omitting topic returns (all topics interleaved by arrival time plus the distinct-topic list) and what passing it returns (raw, single conversation). It does not restate the limit parameter, but the schema handles that adequately.

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+resource ('Read what mesh_observe_lobby has recorded') and immediately scopes it as a local SQLite read. It explicitly positions itself against siblings, calling out mesh_read_inbox as the threaded view and mesh_observe_lobby as the recorder, so an agent can distinguish it 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?

Gives explicit when-to-use branches: omit topic to see all interleaved traffic plus the distinct-topic list, or pass topic to read one conversation raw. It names the alternative tool (mesh_read_inbox) and the condition that selects it ('the rooms you are actually in'), which is exactly the routing guidance an agent needs.

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