Act on a thread

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

Annotations already flag the tool as destructive and non-read-only, but the description adds concrete behavioral consequences: deletion is permanent and support creates a request with the platform team. It also describes the read-state change for `mark_read`. This is valuable context beyond the annotation flags, though it does not cover auth, rate limits, or post-action confirmation.

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?

A single, tightly written sentence covers all three actions with no filler, using code formatting for the enum values. Every phrase contributes operational meaning, and the most important caveat (`permanently`) is embedded directly.

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 a three-action mutation tool, the description plus schema is largely sufficient: all actions are defined, the destructive consequence is explicit, and the schema covers parameter meanings and conditional requirements. It falls short only in not stating the expected response or confirmation for each action and not explicitly tying `message` to `support`, but these are minor given the lack of an output schema.

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 schema already describes `thread_id` and `message` and enumerates `action`, so coverage is decent at 67%. The description reinforces the meaning of each action but does not clarify conditional parameter requirements—such as explicitly tying `message` to the `support` action—beyond what the schema already states. It adds only marginal value over the input 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?

The description enumerates every action with a concrete verb and object: `mark_read` clears the unread flag, `delete` removes the thread permanently, and `support` opens a support request. This goes beyond the generic title and lets an agent distinguish thread mutations from sibling read tools like `list_threads` and `get_thread`.

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 makes the available operations and their effects clear, so intended use is inferable: mark a thread read, delete it, or file a support request. However, it never explicitly contrasts this with alternatives or states when not to use it, leaving the agent to infer routing from sibling tool names and action semantics.

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