flag_thread

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

Annotations only provide destructiveHint: false, leaving the description to carry the behavioral burden. The description discloses that flag operations are gated by PROTONMAIL_ALLOWED_ACTIONS and that setting \Deleted requires confirmed:true when PROTONMAIL_CONFIRM_DESTRUCTIVE is enabled. This adds meaningful context beyond the annotations. It doesn't mention dryRun behavior or response format, but given the sparse annotations, this is a solid disclosure.

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 four sentences long and front-loads the core purpose in the first clause. Each subsequent sentence adds distinct information: usage guidance, alternative, and gating details. It is dense but not bloated, and the structure flows logically from purpose to guidance to constraints.

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 6 parameters, no output schema, and only 33% schema coverage, the description leaves notable gaps. It does not explain the format or constraints for flagsToAdd/flagsToRemove, the effect of acrossFolders, or what dryRun does. It also omits any mention of return values or errors. While it covers the primary use case and gating, the tool is complex enough that this is incomplete.

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 description coverage is only 33%, so the description must compensate. It clarifies messageId (RFC 5322) and confirmed (gating requirement) and gives concrete flag examples (\Seen, \Flagged, \Deleted). However, it does not explain flagsToAdd/flagsToRemove value semantics, acrossFolders behavior, or dryRun's effect, which are undocumented in both schema and description. It adds some value but not enough to fully compensate for the low coverage.

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 precise statement of action ('Add or remove IMAP flags') and scope ('across all messages in a thread'), identified by a specific identifier ('RFC 5322 Message-ID'). It clearly differentiates from sibling apply_thread_action by naming the condition (local threadId vs raw Message-ID) and the alternative actions.

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 when-to-use guidance: use when you have the raw Message-ID and want to flag a whole conversation. It also names the preferred alternative (apply_thread_action) and the specific actions (mark_read, mark_unread, star, unstar) when a local threadId is available. Additionally, it explains the gating requirements relative to other tools (mark_email_read, star_email, delete_email).

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