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

Annotations already indicate mutation (readOnlyHint=false) and non-idempotence (idempotentHint=false). The description adds critical context: on IMAP the email ID changes after move/update, so the result.id must be reused. It also warns against using stale IDs. This goes beyond annotations and is essential for correct follow-up calls.

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 long but well-organized, starting with the core purpose and then diving into necessary caveats and resolution steps. It is front-loaded with the key behavior (ID change) and structured into clear sections. While a bit verbose, the complexity of the tool justifies the length; 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?

With no output schema, the description explains the return value ('the email after the change') and the critical ID mutation. It covers ID resolution for both email and folders, warns about common pitfalls, and clarifies account_id handling. It lacks explicit error conditions or edge cases, but covers the primary use cases and traps. Slightly incomplete for specifics parameter, but overall strong.

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 50% (email_id and folders_ids have descriptions; specifics and account_id lack them). The description compensates by providing detailed instructions for email_id and folders_ids, including how to obtain and what not to pass. For specifics and account_id, the description offers some guidance (e.g., account_id resolution), but specifics remains underdocumented. Overall, the description adds significant value beyond the schema.

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 ('Move/label') and resource ('one exact email') with scope. Clearly distinguishes from siblings like email_trash, email_update_draft, and email_send by focusing on moving/labeling. The description also mentions the result is the email after the change, which is unique.

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?

Provides explicit guidance on how to resolve email_id and folder IDs, including specific sources (email_list_messages, email_list_folders) and what to avoid (RFC Message-ID, human folder names). While it doesn't explicitly compare to alternatives like email_trash, it clearly scopes the operation and offers procedural steps. Lacks explicit 'when not to use' but strong on how to use correctly.

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