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

Goes well beyond the destructive/openWorld annotations by disclosing the billing model: the invoker is charged for agent AI and compute, accessed Space owners pay infrastructure usage, included weekly coverage is consumed before purchased Credits, and membership does not confer permission to spend another account's Credits. That is genuinely non-obvious operational context. It stops short of explaining what the destructiveHint actually destroys or what the default 'delete' retention means for the agent's data.

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 tight sentences with the action and required decisions front-loaded, followed by billing semantics. The final permission sentence is slightly dense but carries real value and there is no filler.

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?

The output schema exists, so return values need not be described. However, for a destructive, open-world, 13-parameter tool with nested curator/discussion objects and zero schema descriptions, the description leaves too many invocation-critical decisions unaddressed to be considered complete.

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?

With 0% schema description coverage across 13 parameters, the description must carry the full semantic load, and it only covers read/write Spaces, retention, accepted rate card and max_credits. Curator mode (threads vs supplied), discussion/public_disclosure, cross_space_disclosure, public_research_queries, destination_space_id, idempotency_key and timeout_seconds are left entirely unexplained, which is a substantial gap for a nested 13-parameter tool.

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?

Opening sentence states a specific verb and resource ('Start a funded orchestrator Task'), and 'funded' distinguishes it from the unfunded private_curator_run and private_research_run siblings. It never names those siblings or explicitly states the difference, so the differentiation is implied by an adjective rather than spelled out.

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?

It implies when to use it by listing the decisions the caller must make (read/write Spaces, retention, rate card, budget), which gives the agent a pre-flight checklist. But there is no explicit guidance on when to pick orchestrator over curator_run or research_run, and no stated prerequisites such as budget authorization or rate-card acceptance flow.

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