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

Beyond the readOnlyHint annotations, the description discloses that events are not consumed, no coins are spent, payloads are untrusted, and sender signatures are not verified. This is valuable behavioral context that structured annotations alone do not provide, and it does not contradict any annotation.

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 adds meaningful information. There is no filler or repetition of schema data.

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?

The output schema covers return-value structure, and the description adds pagination, security, and consumption behavior. Given the tool moderate complexity, this is nearly complete; the only small gap is the lack of any note about the exact structure or error conditions for the cursor, but the presence of an output schema reduces that burden.

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 compensate for parameter meanings. It adds semantics for the cursor behavior via 'after' and 'next_cursor', but it does not explain api_key or inbox_id, leaving two of three parameters dependent on agent inference.

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 specific operation: reading up to 20 callback events after a cursor. It also distinguishes the tool from siblings like create_callback_inbox and list_callback_inboxes by focusing on event consumption and pagination.

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 usage context: use it to read a bounded window of events after a cursor without consuming them, and persist next_cursor to continue. It does not explicitly name alternatives or exclusions, but the pagination and non-consuming behavior effectively disambiguate when this tool is appropriate.

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