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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered; the description adds the genuinely non-obvious behavior that only locally downloaded messages are visible on IMAP accounts and that results are paged. It does not state ordering guarantees beyond "newest first" or any rate/size limits, but for a read-only list tool that is a minor gap.

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 compact sentences: what it returns and in what order, how to supply the folder and pagination, then the caveat about partial IMAP visibility. Zero filler and the most important constraint is front-loaded.

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, the description needn't detail return shape, yet it does briefly and helpfully. It covers folder resolution, paging, and the IMAP limitation; it omits any mention of the account/profile parameters, though the schema covers those adequately.

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 documents all five parameters and the baseline is 3. The description reinforces the most error-prone one — that folder is a path derived from thunderbird_list_accounts (e.g. INBOX/Work) and defaults to INBOX — but adds nothing about account or profile, leaving the heavy lifting to 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?

"Lists the newest messages of one Thunderbird folder, newest first" is a specific verb+resource+ordering, and the field enumeration (id, sender, recipients, subject, date, size, flags) pins down what a listing contains. It stops short of naming the sibling it must not be confused with (thunderbird_search_emails), so selection still requires inference.

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 implied by "newest messages of one folder" and by directing the agent to thunderbird_list_accounts for the folder path, but there is no explicit "use this when you want an unfiltered browse; use thunderbird_search_emails when you have criteria." The IMAP caveat tells the agent to expect incomplete results, which is a useful caution rather than routing guidance.

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