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

Discloses the state-mutating side effect ('Marks them read') and the side effect of writing a line into Min AI for each chat — this is real behavioral context. Notably annotations claim idempotentHint=false and readOnlyHint=true, yet the description says it marks messages read (a mutation); readOnlyHint=true is arguably contradicted by a state-changing write to message read-status. This is a partial contradiction worth flagging.

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 action and scope, then guidance and side effects. Reasonably tight, though the parenthetical caps plus the summarizing flow plus the Min AI line make it a dense run-on; still, every clause carries information.

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?

Covers action, limits, side effects, and the recommended agent follow-up. Output schema exists so return-shape need not be explained. The main gap is not clarifying relationship to read_conversation for single-conversation cases.

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% and the single optional param (maxConversations, default 5, max 8) is documented in-schema. The description mentions the '8 conversations' cap but doesn't explain maxConversations semantics beyond what the schema already states, so baseline 3.

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 and resource with scope: reads UNREAD messages across conversations, newest first, with explicit caps (20 messages/conversation, 8 conversations). Clearly distinguishes itself from read_conversation (singular, one conversation) via the 'across their conversations in one call' phrasing.

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 trigger phrases ('what did people write?' / 'read my unread') and the follow-up flow (summarize, then ask what to reply). Doesn't name the sibling alternative read_conversation as a fallback for single-conversation reads, but the batch scope makes the boundary fairly inferable.

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