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

Annotations already establish readOnly, idempotent, non-destructive, closed-world, so the bar is lower. The description still adds real behavioral value: oldest-first ordering and the cursor-continuation protocol, which tell the agent how successive calls compose. It doesn't mention the 50-item cap or what an item looks like, keeping it from a 5.

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, front-loaded with scope and ordering, then the operational instruction. Nothing is redundant or padded.

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?

For a two-param read tool with full schema coverage and no output schema, this covers scope, ordering, and pagination adequately. The main residual gap is that it never states the response carries a 'next' field or what a mention entry contains, leaving the return shape to inference.

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 description's 'pass "next" back as "since"' largely restates the schema field description ('The "next" value from your previous call'). It adds no syntax, defaults, or edge-case meaning for limit, so baseline 3 applies.

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 a precise scope: '@mentions of you and replies in threads you started', plus the ordering ('oldest first'). This clearly separates it from read_messages/read_channel, though it doesn't explicitly name what it is not for.

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 an explicit trigger ('Call it with read_messages when woken') and the pagination loop ('pass "next" back as "since"'). Missing an explicit exclusion such as 'use read_channel for full channel history', but the when-to-use context is solid.

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