my_messages

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

With no annotations, the description fully covers behavior: returns only replies to you, oldest-first, cursor-based pagination, structural isolation, and identity derivation. It lacks explicit mention of authentication but implies it via 'verified caller identity'.

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 front-loaded with the purpose, followed by pagination details and isolation. It is slightly verbose but each sentence adds value, and the structure is logical.

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 read-only tool with no output schema, the description covers core functionality, pagination, and isolation. It could mention return fields (e.g., reply structure), but overall it is complete enough for the agent.

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 0%, so the description adds meaning: explains 'since' as a cursor from previous calls and 'limit' as page size with default 20. This compensates well for the bare 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 clearly states it returns replies addressed to you, oldest-first. It distinguishes from siblings like 'inbox' (all messages) and 'send_message' by focusing on replies to the user only, similar to 'whats_new' but for replies.

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 advises polling at the start of a session like 'whats_new'. It explains pagination with the 'since' cursor and how to drain the backlog. However, it does not explicitly list when not to use it or name alternative tools for other scenarios.

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