thunderbird_list_emails

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

With no annotations, the description carries the full behavioral burden. It discloses ordering and a partial field list, but says nothing about result limits, pagination, how many messages are returned, or authentication requirements. The truncated ending also leaves the disclosure incomplete.

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 visible text is a single front-loaded sentence with no filler, opening with the verb and resource and immediately giving ordering. The truncated ending is a delivery defect rather than verbosity, so it does not penalize concision itself.

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 zero-parameter tool with no output schema, the description does helpfully enumerate returned fields (id, sender, recipients, subject, date...), which substitutes for the missing output schema. But it claims the tool targets 'one Thunderbird folder' while offering no folder parameter, and the sentence is cut off, leaving the caller unable to resolve how the folder and result set are determined.

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?

The schema defines zero parameters, so there is no parameter semantics for the description to add. Per the baseline for parameterless tools, this is adequate. This does, however, raise an unresolved question about which folder is used when no folder argument exists.

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?

States a specific verb and resource (lists the newest messages of a Thunderbird folder) and notes the ordering (newest first), which distinguishes it from thunderbird_search_emails and thunderbird_read_email. However, the text is truncated mid-sentence, so the full purpose statement and its differentiation from siblings remain partially unstated.

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?

No explicit when-to-use guidance is given. It never states when to pick this over thunderbird_search_emails, thunderbird_read_email, or the generic list_emails/list_messages siblings, nor any prerequisite such as an active Thunderbird connection. Usage must be inferred solely from the words 'newest messages'.

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