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

Annotations already declare openWorldHint=true and destructiveHint=true, yet the description adds genuinely new behavior: who pays for what (invoker charged for agent AI/compute, Space owners charged infrastructure), that included weekly coverage is consumed before purchased Credits, and a cross-account permission boundary. It does not spell out the destructive consequence implied by destructiveHint (e.g. what retention=delete removes), which keeps it from a 5.

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?

Purpose is front-loaded in the first sentence and the remaining sentences carry distinct, non-redundant information about billing and permission. The credit-coverage and membership sentences could be tightened, and the parameter expectations are buried in prose rather than enumerated.

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 13-parameter, nested-object, cost-incurring, destructive operation, the description covers only a handful of inputs and omits the curator/discussion/disclosure surface entirely. The output schema does relieve it of explaining return values, but the configuration surface an agent must fill in correctly is largely undocumented.

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 0% across 13 parameters including deeply nested objects, so the description must compensate and largely does not. It names read/write spaces, retention, rate card and max credits, but leaves curator, discussion.*, cross_space_disclosure, destination_space_id, public_research_queries, idempotency_key and timeout_seconds entirely unexplained in both schema and prose.

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?

Opens with a specific verb+resource: "Start a funded research Task." That is clearly distinct from list/read siblings. It never names or contrasts with the very similar private_curator_run, private_orchestrator_run, or private_support_run, so an agent cannot confidently choose among the run-family without opening schemas.

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?

"Select exact read and write Spaces, retention, the accepted rate card and a maximum Credit budget" implies the setup required before invoking, which is real usage context. But there is no explicit when-to-use/when-not, no mention of prerequisites like the agent setup/delegation siblings, and no routing away from the other *_run tools.

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