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

Goes well beyond readOnlyHint/openWorldHint by disclosing that Thunderbird need not be running, that nothing in the profile is modified, that the result is count 0 when no profile exists, and how the `permissions` sub-object should be interpreted including the read_only override. These are exactly the operational facts an agent cannot get from 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?

Front-loaded with the resource and the 'start here' routing cue, then caveats, then the permissions decoding. The final permissions sentence is dense and uses internal UI navigation syntax ('LMCP's icon → My apps → open the app's row') that costs more space than it returns.

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?

Even though an output schema exists, the description covers the empty-result case, the local-only visibility limitation, and the permissions semantics, leaving nothing an agent needs before calling it unresolved.

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% and the single optional `profile` parameter is fully documented there, so the schema does the work. The description only alludes to 'the Thunderbird profile on this computer' without explaining default-vs-named profile selection, so baseline 3 applies.

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 mail accounts of the Thunderbird profile') and enumerates the returned fields (id, name, address, type, folders, local-storage flag, message counts), which separates it cleanly from thunderbird_list_emails and thunderbird_read_email.

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?

Explicitly tells the agent to start here because the other thunderbird_* tools take an account and folder from this list, giving a concrete ordering constraint rather than implied usage. It also sets the expectation that only locally-stored messages are visible for IMAP, which pre-empts a wrong sibling choice.

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