workflow_checkpoint

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

Discloses atomicity, idempotency (overwrite on re-checkpoint), and valid output types (JSON-serializable). Without annotations, this covers key behaviors, but lacks details on error handling, required permissions, or 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?

Three concise sentences in two paragraphs; no wasted words. Could be more logically ordered (e.g., parameters first), but overall efficient.

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?

Covers core functionality, usage, and idempotency. Output schema exists (not shown) so return value is covered there. Missing prerequisites (workflow must exist) and failure scenarios, but still reasonably complete for a checkpoint tool.

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 coverage is 0%: no parameter descriptions in the description. While 'step' is implied in usage context, 'run_id' is not explained at all, and 'output' is described as JSON-serializable but without constraints. Description adds limited semantic value beyond the schema.

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?

Description clearly states the tool persists checkpoint data and advances step counter, with specific verb 'persist' and resource 'completed step's output'. However, it does not explicitly differentiate from siblings like state_set or workflow_create, though mentioning workflow_resume as complementary.

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?

Explicitly states 'Call this immediately after each pipeline step completes, before starting the next one', providing clear when-to-use. Mentions workflow_resume as the partner for resumption, implying when not to use directly.

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