Plan a direct-intake Working Revision

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: the server never calls a model or executes code, and the resulting plan is immutable — which tells the agent this call is inert and safe to re-run while producing no side effects.

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?

Two sentences, both front-loaded with the core verb and the key negative constraint ('never calls a model or executes code'), with no filler. It is efficient, though arguably under-sized for a 31-parameter tool.

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?

Given 31 parameters, zero required fields, near-zero schema coverage, and no output schema, the description is far too thin: it does not explain what a 'Working Revision plan' contains, what the confirmations flags gate, or what distinguishes create vs update mode. The inert-server statement is useful but nowhere near sufficient for a tool of this complexity.

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 31 parameters and only 3% schema description coverage, the schema explains essentially nothing, so the description carries the full burden — yet it adds no parameter meaning at all. It only loosely gestures at the confirmations/intake concepts via 'user-confirmed image/code intake', leaving enums, nested runtime/codeAssets/validationState structures, and the confirmations object completely undocumented.

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 gives a specific verb pair ('validate ... return an immutable Working Revision plan') and a specific resource, so the agent knows it is a planning/validation step rather than a mutation. It does not name the sibling that actually persists the plan (figure_library_apply_working_revision), so differentiation rests on the plan/apply naming convention rather than explicit text.

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 phrase 'user-confirmed image/code intake' implies a precondition (the intake must already be confirmed by the user) but never states when to call this versus apply_working_revision, publish_working_revision, or discard_working_revision. Usage is inferable from the plan/apply sibling pairing, not stated.

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