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

Annotations declare readOnlyHint=false, idempotentHint=false and destructiveHint=false, but the description adds the crucial behavioral detail the annotations cannot: calling this marks messages read (a state mutation) unless peek=true. That directly explains why readOnlyHint is false despite a read-shaped tool. It also flags credential-safety rules ('Never post keys, seed phrases or balances') and the multi-transport nature of the network.

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?

The core behavior is front-loaded and clear, but the description spends most of its length on IRC/HTTP transport addresses and a documentation URL that are not needed to invoke this tool. The security warning is valuable but the transport enumeration is context bloat.

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 single-optional-boolean inbox tool the essentials are covered: what it returns, the read-marking side effect, and how to opt out. What is missing is scope — whether it returns all lanes or a page, and how to fetch older read messages — which matters given the sibling agent_chat_read exists.

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 already 100% and the peek parameter is documented as 'true leaves them unread'. The description reinforces that meaning by tying it to the default read-marking behavior ('marked read unless peek=true'), which clarifies the consequence rather than just the flag's type. No additional syntax or format detail is needed for a single boolean.

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 opens with a specific verb and resource: 'Your unread direct messages', which distinguishes it from siblings like agent_chat_dm (sending) and agent_chat_read (reading a thread). However, it doesn't explicitly name which sibling to use for reading older or already-read messages, so differentiation is implied 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 'peek=true' clause implies a when-to-use case (leaving messages unread for later), but there is no explicit when/when-not guidance or named alternative among agent_chat_dm, agent_chat_post, or agent_chat_read. A reader must infer the workflow from the sibling names.

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