Apply atomic approval and publication

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

Going beyond the idempotentHint annotation, the description reveals operation-id scoped idempotency and stale-state validation. This tells the agent that expectedTemplateId/expectedSeriesDigest are used as optimistic concurrency guards and that retries are safe. However, it omits failure behavior (e.g., what error does a stale state return?) and the full set of 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?

The description is a single 15-word sentence starting with the imperative verb. Every phrase pulls weight: 'exact' clarifies planDigest fidelity, 'operation-id' names the idempotency key, and 'stale-state checks' flags concurrency. No filler or repetition of the name.

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 mutating publish/commit tool with four required parameters and no output schema, many essential details are absent: what is the success/failure return shape? What if the cached plan is missing or invalid? What are the synchronization semantics with figure_library_plan_publish_working_revision? The description assumes the agent comprehends a complex distributed workflow (plan-cache-apply-publish) without adequate guardrails.

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 coverage, the description carries the burden and does provide oblique references: 'exact cached plan' → planDigest, 'operation-id' → operationId, 'stale-state checks' → expectedTemplateId/expectedSeriesDigest. Yet the mapping is never made explicit, forcing the agent to infer meaning, and the concurrency tokens' checkpoint role is only implied.

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 uses a specific verb 'Apply' followed by a concrete object ('the exact cached plan') and qualifiers that differentiate it from siblings like figure_library_plan_publish_working_revision. The title adds 'atomic approval and publication' context. However, it doesn't explicitly state 'publish a working revision' in the description, which would make it unmistakable.

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 implies a two-phase flow through 'cached plan' (planning must precede) and 'operation-id idempotency' (safe retries after a previous attempt). But it never explicitly contrasts with alternatives like figure_library_apply_working_revision or states when to use this versus the plan_* counterpart. No explicit when-to-use or exclusions.

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