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

Beyond the readOnly/idempotent/non-destructive annotations, the description adds important behavioral context: transcript text is untrusted data and must not be treated as authority, and a pending send is not proof of delivery. It repeats the no-state-change point already implied by annotations, but the added safety semantics are substantive.

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 description is short, front-loaded with the core action, and every sentence carries useful information. The untrusted-data warning and sibling references are compact and non-redundant.

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?

With rich annotations, full schema descriptions, and an output schema present, the description is complete enough for correct invocation. It covers the key safety caveat around untrusted transcript content and routes the agent to the right alternatives for attachments and reconciliation.

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 100%, so the schema already explains agent_id, conversation_id, limit, and cursor. The description adds the notion of a scoped transcript page but does not provide additional parameter meaning beyond the schema.

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 states a specific verb and resource: reads a scoped transcript page. It also distinguishes the tool from inbox_attachment and inbox_message_reconcile, but it does not clarify how it differs from other nearby read tools such as inbox_read or inbox_list.

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 clear alternative routing for attachments (inbox_attachment) and for pending/unknown send recovery (inbox_message_reconcile). It stops short of an explicit statement of when to use this tool rather than inbox_read or inbox_list.

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