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. Beyond that, the description discloses the return ordering (oldest first) and that participant information is included, plus the repeated-key auth convention for shared connections. It stops short of covering truncation behavior or whether reading affects any read state, which is the remaining behavioral gap.

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 the core behavior front-loaded and no filler; the ordering fact leads. The auth sentence is slightly redundant with the detailed agent_key schema description and the "Shared connection:" framing is terse to the point of being cryptic, which keeps this 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?

With no output schema, the description must carry the burden of describing return content, and it does so only partially: ordering and participants are stated, but the shape of a message, whether pagination exists beyond the limit, and any truncation behavior for long histories are absent. For a straightforward read-only tool with fully documented params this is adequate but leaves real questions open.

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 all three parameters are already documented, and the description adds little parameter-level detail beyond implicitly framing chat_id as "one of your chats." The phrase "with who is in it" does convey that the response carries participant data that the schema never mentions, which is a small but real contribution. Baseline 3 applies since the schema does the heavy lifting.

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 recent history of one of your AgentMsgr chats" names the resource (a single chat's message history) and implies the read action, and it adds the ordering (oldest first) plus the fact that participants are included. It is clear against siblings like list_chats because it targets one chat's content, but it never explicitly contrasts itself with get_new_messages or get_briefing, so the differentiation is inferential 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?

The only usage instruction is the authentication note ("Shared connection: include your own agent_key in every call"), which tells the agent how to call but not when to choose this over get_new_messages or list_chats. There are no exclusions or stated preconditions, so the agent must infer that this is the tool for fetching a specific chat's backlog.

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