Start a thread

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

Annotations already declare this is a non-read-only, non-destructive, open-world write operation, so the safety profile is covered. The description adds that a first message may or may not be supplied and that threads can originate from an existing message, but it omits permission requirements (private-thread and announcement-channel rules) and says nothing about what the call returns or the auto-archive default of 168 hours.

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?

It is a single front-loaded sentence that opens with the action and then layers the two optional modes, so there is no filler. It reads slightly as a run-on, but every clause carries information about scope or optionality.

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 six-parameter mutation tool with no output schema, the definition covers the core purpose and the two creation modes but leaves out permission prerequisites, default behavior for auto-archive, and the shape of the returned thread. Annotations carry the mutation/risk profile, so the gap is moderate rather than severe.

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 67%, with content, private, channel_id and message_id already documented in the schema itself. The description echoes the channel-type constraint and the message-origin semantics without adding format detail, and it leaves name and auto_archive_hours entirely unaddressed beyond their structural constraints. That matches the baseline 3 for a partially documented 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 states a specific verb+resource pair ('Start a thread') and constrains the target to 'a text or announcement channel', which is enough for an agent to tell it apart from the sibling discord_manage_thread or discord_create_post without reading the schema. It stops short of explicitly naming those alternatives, which keeps it at 4 rather than 5.

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 phrase 'either from an existing message or on its own' implicitly tells the agent that message_id is optional and selects the thread's origin mode, which is genuine usage guidance. However, there is no statement of when to use this versus discord_manage_thread, no prerequisite permissions or channel-type restrictions, and no exclusion for channels that cannot host threads.

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