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

Annotations already declare readOnly, idempotent, closed-world, and non-destructive, so the safety profile is covered. The description still adds real value by disclosing privacy scope ('PRIVATE'), ordering ('newest first'), and the non-obvious side effect that reads do not acknowledge messages, which annotations cannot express.

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?

Three tight fragments with zero filler, and the most decision-relevant facts (read-only, private, ordering) are front-loaded. Every clause carries information an agent needs.

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 an output schema present, return values need not be described, and annotations cover the safety profile. The remaining gap is that page-size behavior is left entirely to the schema, but overall the definition is sufficient for correct invocation.

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 50%: 'before' is documented in the schema as a cursor from next_cursor, while 'limit' is undocumented there. The description's 'with a cursor' and 'newest first' reinforce how pagination works but say nothing about the page-size parameter or its bounds, so it only marginally exceeds 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 gives a specific verb and resource ('Read ... Replies to this identity's questions'), plus ordering ('newest first') and pagination ('with a cursor'). The line 'Reading never acknowledges' implicitly distinguishes it from the acknowledge_inbox sibling, so an agent can pick between them without opening a schema.

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?

Usage context is clear: this pulls the private reply stream for the current identity, and the clarifying phrase 'Reading never acknowledges' signals that acknowledging is a separate action (acknowledge_inbox). That contrast is helpful but stated obliquely rather than as an explicit 'use X instead when...' rule.

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