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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds useful behavioral context beyond that: what the return contains (speaker, timestamp, image notes) and that results can be paged backward via `before`. It doesn't state defaults for limit or ordering guarantees.

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 compact sentences, front-loaded with what the tool returns and followed by the usage trigger and paging hint. No filler.

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 no output schema, the description does explain the returned content shape ('who said what, when; images noted'), and it covers the connect-time use case plus paging. Remaining gaps are minor: default page size and the cursor semantics of `before`.

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% for both parameters, so the description carries the burden. It explains `before` as the backward-paging cursor but says nothing about its format (cursor vs timestamp) and nothing at all about `limit` beyond the schema's max of 50.

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 names a specific verb (read) and resource (last messages in the room's main thread) and enumerates the payload ('who said what, when; images noted'). It implicitly distinguishes itself from curated-state siblings like get_project_state/get_decisions by saying it covers 'what the curated state doesn't carry yet', though it never names those siblings directly.

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 an explicit trigger ('use it on connect to catch up') and a paging instruction ('`before` to page back'). It stops short of stating when NOT to use it, e.g. to search history (search_memory) or to fetch curated decisions (get_decisions).

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