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

Annotations already declare readOnlyHint and destructiveHint=false, yet the description still adds real value: 'Nothing is marked as read' resolves the common ambiguity for mail-listing tools, and 'requires a Proton plan that includes Bridge, with Bridge running' discloses a hard precondition the agent must check. It stops short of 5 because pagination limits (max 200) and total-count behavior are left to the schema.

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?

One compact paragraph, front-loaded with what is returned and then the paging, safety, and environment notes. Every sentence carries information, though the folder-naming and paging clauses are packed densely enough that a lightly structured sentence split would read better.

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, return values need not be described, and the description still covers defaults, folder naming, paging, non-mutation semantics, and the Bridge dependency. Only the default account behavior (when 'account' may be omitted) is delegated entirely to the schema rather than reinforced here.

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 baseline is 3; the description goes beyond it by enumerating Bridge's concrete folder names (Sent, Archive, All Mail, Folders/…, Labels/…) and repeating the limit/offset paging model. That naming convention is genuinely extra information an agent cannot infer from a plain 'folder name' schema field.

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 names a specific verb and resource ('Lists the newest messages of one folder of a Proton Mail account') and states the returned fields and sort order, so the agent knows exactly what comes back. It does not name the sibling that would be the alternative for filtered retrieval (proton_search_emails) or distinguish itself from m365_list_emails/thunderbird_list_emails, which keeps it short of a 5.

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 'one folder ... newest first' and by the folder examples, but there is no explicit statement of when to prefer this over proton_search_emails or when browsing is the wrong approach. The Bridge prerequisite is the closest thing to a usage condition.

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