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

Annotations already carry readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description still adds non-obvious operational context: 'no signature' required (an auth/invocation detail not in the schema) and the pagination ceiling behavior, which matters for a read that can span many conversations.

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 short sentences, front-loaded with the core action and scope. The pagination sentence largely duplicates schema-declared defaults (default 50, max 200), which is the only sentence that does not fully earn 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?

With no output schema and zero required parameters, the description covers scope, auth requirement, grouping granularity, and pagination — enough to call it correctly. It stops short of describing what a conversation entry contains (e.g. unread counts, latest message, ordering), which is the only meaningful remaining gap for a read tool.

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 100%, so the schema already documents all three parameters including defaults and bounds. The description restates the offset/limit defaults and adds only a light gloss on `caller` ('the account whose view to read'), which is marginally more informative than the schema's 'run the query as' but not enough to exceed the baseline.

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?

Specific verb+resource: 'Get caller's private-message inbox, grouped by conversation.' The 'grouped by conversation' qualifier implicitly separates it from the sibling inbox tools (get_my_inbox_groups, get_my_inbox_lists, get_my_paid_inbox), but none of those siblings are named, so the differentiation is left to inference rather than stated.

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 is only implied: an agent must deduce that group messages live in get_my_inbox_groups, list messages in get_my_inbox_lists, and paid messages in get_my_paid_inbox. There is no explicit 'use X instead when...' guidance and no exclusion for those adjacent tools, despite six close siblings in the messaging family.

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