inbox

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

No annotations are provided, so the description carries full responsibility. It discloses the read nature and the permission model, but it does not mention that mark_read can mutate state (mark messages as read). This is a behavioral gap, as an agent might assume a purely read-only operation despite the parameter hinting at a 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?

Two sentences with no filler. The primary purpose is stated first, followed by the access rule. Every word earns its place.

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 tool with 3 parameters, no output schema, and no annotations, the description is incomplete. It fails to explain mark_read and unread_only, and does not describe the return format. An agent would be guessing on how to use the tool effectively.

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 description coverage is 0%, so the description must explain all parameters. It only explains agent_id (and who needs it), leaving mark_read and unread_only completely undefined. The agent cannot know what these booleans do without external knowledge, which is a significant deficiency.

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 the tool's function ('Read persisted messages') and distinguishes it from sending tools like send and message_send. It also specifies the resource (messages) and the context for who can read what, which sets it apart from siblings.

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 explicitly explains when agent_id must be specified (external supervisors) and implies it's optional for managed agents. This gives concrete usage guidance, though it doesn't explicitly name alternatives or state 'use this when you need to read messages' – but that is clear from the verb 'read'.

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