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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses that specialists are deterministic stubs today, that each request creates an approval-gated action landing in the Launch Room, and that `runId` grounds output in the originating launch brief. It does not mention auth requirements or exact output envelope details, but the key side effects are covered.

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 front-loaded with the core purpose and uses a scannable 'USE WHEN' pattern with the kind list. It is slightly longer than necessary due to the 'Future LLM-backed implementations swap in transparently' sentence and some redundancy with the `autoCreateAction` schema description, but still organized and efficient.

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 5-parameter tool with a nested `brief` object and no output schema, the description covers purpose, use cases, deterministic behavior, side effects, and runId grounding. It could more explicitly state the return shape beyond 'structured briefs / plans / drafts' and mention error cases, but the provided information is sufficient for an agent to select and invoke correctly.

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 by translating the `kind` enum values into concrete real-world artifacts and by explaining the purpose of `runId`—grounding in the launch brief. It relies on the schema for `brief`'s internal structure, but that's acceptable given the schema descriptions are already detailed.

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 explicitly names the resource ('specialist agent') and uses a specific verb ('delegate'), then maps six `kind` values to concrete deliverables (graphic brief, video shot list, research plan, outreach drafts, SEO recommendations, analytics verdict). This clearly distinguishes it from sibling tools like `list_specialists` or `create_work_request` by scoping the purpose to specialist delegation.

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 opens with 'USE WHEN the launch needs more than copy' and enumerates specific scenarios per `kind`, giving an agent clear conditions to invoke the tool. It does not explicitly name alternative tools or provide when-not-to-use guidance, so it lacks full exclusion semantics.

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