Restart Thunderbird

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

Annotations already indicate destructiveHint=true. The description adds critical behavioral context: every in-flight call fails, the bridge connection drops, the tool returns before restart completes, and unsent compose windows/drafts are lost. This goes well beyond the annotations.

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 description is concise with no wasted words. It front-loads the core action, then efficiently lists side effects, post-action steps, and usage advice. Every sentence adds value.

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?

Given the tool's destructive nature and side effects, the description covers all necessary facets: what happens to other calls, return behavior, lost data, user consent, and follow-up action. It is complete for an agent to use safely.

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 only parameter is 'confirm'. The description explicitly says 'ask the user before you do it', which directly maps to the confirm parameter's purpose. With 0% schema coverage, the description fully compensates by explaining the parameter's role.

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 clearly states 'Restart Thunderbird' as the verb+resource. It distinguishes itself from sibling tools like tb_status and tb_wait by specifying the restart action, and the additional details about in-flight calls failing and losing unsaved data provide context without ambiguity.

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?

The description explicitly advises when to use (restart Thunderbird) and when not to (a stuck sync usually does not need it). It also instructs to ask the user before proceeding and to wait with tb_wait afterwards, providing clear guidance on usage and alternatives.

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