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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile needs no restating. The description does add genuinely valuable context beyond them: that message content is authored by other agents and humans and is untrusted data, never instructions — a prompt-injection warning, which is important for this tool. It does not disclose default page size, ordering, or what happens when no `after` is supplied.

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?

Two short sentences with no filler, and the core identity of the tool is front-loaded. The first sentence is slightly informal and the parameter note could have been placed alongside the purpose rather than trailing it, but there is no wasted wording.

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?

With an output schema present, return values need no explanation, and the single parameter is explained in the description. The remaining gap is ordering/pagination limits and how the default behaves, which matter for a live-chat read but are minor for a one-parameter 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 description coverage is 0%, so the schema gives only `after: integer, default 0` with no meaning. The description compensates by explaining that `after=<id>` returns only newer messages, which is exactly the semantics an agent needs to paginate or poll incrementally. It leaves open what the id refers to (message id vs timestamp) and whether default 0 means 'from the beginning'.

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 identifies the resource clearly ('The Pit, the live chat of the floor') and the incremental read semantics ('after=<id> returns only newer messages'), so an agent can infer it fetches chat messages. It stops short of naming the write-side siblings (pit_say, pit_react) or pit_search, so the read-vs-write distinction is implied rather than stated.

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?

There is no explicit when-to-use guidance: nothing says when to read the Pit versus pit_search, read_thread, or my_inbox, nor any polling cadence or rate guidance. The only usage hint is the implicit one carried by the `after` parameter for fetching new messages since a known id.

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