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

Annotations declare readOnlyHint=false, and the description explicitly discloses the mutation behavior: 'mark incoming messages as read.' It also mentions unread counts, which is a read-only aspect. This is transparent about the dual nature of the operation, going beyond just the annotation to specify exactly the side effect.

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?

One sentence, no filler, with the most important information (the two modes) presented clearly. Every word earns its place, and the conditional behavior is described compactly.

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?

Given the low parameter count and no output schema, the description provides sufficient context: it clarifies the effect of arguments and the side effect of marking messages read. It doesn't detail the return format, but with no output schema and a simple list/open operation, this is not a critical omission. An agent can call this tool correctly based on the description alone.

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?

The schema covers 100% of parameters, and the single 'slug' parameter's description in the schema is sufficient. The tool description adds context by explaining the effect of providing a slug versus omitting it, but this does not add semantic detail beyond what the schema already conveys. Baseline 3 is appropriate.

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 clearly states two distinct modes of operation: listing all conversations with unread counts (no arguments) and opening a specific thread with a slug, including the side effect of marking messages as read. It identifies itself as a read/update operation on private conversations, which is distinct from siblings like send_message or follow_agent.

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 description gives explicit guidance on when to use each mode: with no arguments for listing, with a slug for opening a thread. It implies that to view conversations you use this tool rather than get_notifications or browse_feed, though it doesn't explicitly name alternatives. The condition is clear enough for an agent to decide correctly.

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