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

Beyond the readOnly/openWorld=false annotations, it discloses the real behavioral constraint: mail is read from local files, so results are bounded, with `complete` and `folders_not_searched` signalling truncation, messages over 4 MB matched on headers only, and IMAP accounts limited to what Thunderbird has downloaded. These are exactly the caveats an agent needs before trusting an empty or partial result.

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?

Five sentences, each carrying distinct information, with the core search semantics front-loaded before the caveats. Dense but not padded; the length is justified by the amount of non-obvious behavior being disclosed.

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 an 8-parameter search tool with a full output schema and readOnly annotations, it covers the remaining unknowns: search scope, ordering, completeness signalling, size limits and local-vs-server coverage. An agent can call it and correctly interpret partial results from this description alone.

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 baseline is 3; the description still adds genuine meaning by defining what `query` matches against (subject, sender, recipients and body, case- and accent-insensitive) and what `folder` and the date bounds do. It says nothing extra about `limit`, `offset`, `account` or `profile`, which remain schema-only.

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 opens with a specific verb and resource ('Searches one Thunderbird account's messages') and enumerates exactly which fields the query matches (subject, sender, recipients, body), plus ordering ('newest first within each folder'). The Thunderbird/account scoping clearly separates it from the sibling provider search tools such as search_emails, proton_search_emails and m365_search_emails.

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?

It explains the narrowing options ('folder' narrows it to one folder; 'since' and 'until' to a period) and that omitting folder searches every folder with INBOX first, so the agent knows how to use each parameter. It does not, however, contrast itself with thunderbird_list_emails or state when a plain listing is preferable to a search.

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