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

Annotations already cover read-only, idempotent, and non-destructive behavior, so the description is free to add value elsewhere. It discloses result ordering, the meaning of activated_only, and the fields each thread carries (anchor, version, preview, agent_activated) — useful behavior beyond the structured metadata.

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?

Three sentences with no filler: the main action and ordering come first, the key filter guidance follows, and the payload summary closes. Every sentence earns its place.

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 a full schema, rich annotations, an output schema, and this description covering ordering, filtering semantics, and response contents, an agent has everything needed to select and invoke the tool correctly. Pagination and defaults are already covered by the 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?

Schema coverage is 100%, so the baseline is 3. The description adds meaning beyond the schema by explaining that activated_only threads are the actionable ones ('which are the ones you may reply to and resolve'), and it contextualizes the output fields relevant to choosing parameters.

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: 'List the comment threads people left on one of your Artifacts.' It also adds ordering ('newest activity first') and the activated_only filter, making it clearly distinct from the singular get_artifact_thread and the mutation siblings like reply_to_artifact_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 gives concrete guidance on when to use the activated_only filter, noting those are 'the ones you may reply to and resolve.' It implies the list-first workflow before reply/resolve, though it does not explicitly name sibling alternatives or exclusion conditions.

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