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

Annotations already declare destructive=true and readOnly=false, so the mutation status is covered. The description adds genuinely useful context beyond that: who bears cost (invoker for AI/compute, Space owner for infrastructure), that weekly coverage is consumed before purchased Credits, and that membership does not authorize spending another account's Credits. It stops short of explaining what destructiveHint entails (e.g. what retention="delete" removes), leaving a gap.

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 billing/permission notes that follow are substantive rather than filler. It is dense but appropriately sized for a complex, cost-bearing mutation, though the mixed purpose-and-billing sentences could be structured more clearly.

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?

An output schema exists so return values needn't be explained, but for a 13-parameter, nested-object, destructive tool with 0% schema coverage the description is incomplete. It omits the curator mode semantics, disclosure/visibility parameters, research queries, timeout and idempotency behavior that an agent needs to call it safely.

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%, so the description must carry parameter meaning, but it only touches read/write Spaces, retention, rate card and max budget. It says nothing about the 8+ other parameters (curator oneOf modes, discussion/disclosure objects, public_research_queries, timeout_seconds, idempotency_key, destination_space_id), leaving nested and high-risk fields undocumented anywhere.

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+resource ("Start a funded support Task") that clearly names the operation. However, it never distinguishes this from the many near-identical siblings (private_research_run, private_curator_run, private_orchestrator_run), so an agent cannot tell from the description alone which *_run variant is appropriate.

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?

Usage is only implied: the second sentence lists what inputs to select (Spaces, retention, rate card, budget), which gestures at a workflow but never states when to use this tool versus the alternative run tools. There is no explicit when-not condition or alternative routing.

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