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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered by structured data. The description adds context annotations cannot express: the read_token is a private capability that must be guarded, and polling should stop at expiry. It still omits pagination/continuation behavior for a listing operation.

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?

Two short sentences, zero filler, with the core purpose front-loaded and the operational constraint second. Nothing in it is redundant with the name or annotations.

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, the description carries the burden of explaining what comes back, yet it never says whether results are paginated, ordered, or filtered. It covers auth/privacy and token expiry but leaves the return shape and sibling differentiation under-specified for a two-required-param listing 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 50%: read_token is documented in the schema, and the description reinforces that it is private and comes from create_inbox. inbox_id is left unexplained in both places (only a 32-char hex pattern), so the description partially but not fully compensates for the gap.

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?

"Read message summaries in an inbox" gives a specific verb (read), resource (message summaries), and scope (an inbox). The word "summaries" hints at the difference from read_message (full content), but the distinction is left implicit 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?

"Stop polling at expiry" implies this is a poll-style listing tool with a bounded token lifetime, which is useful invocation context. However, it never names read_message or create_inbox as alternatives, so the agent must infer when to list versus read a single message.

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