ddflow_progress

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

With no annotations, the description carries the behavioral disclosure burden. It reveals the source is the event log, stresses 'ACTUALLY' done work, and explicitly says non-pass outcomes are included, which is beyond what the name suggests. It doesn't state read-only safety or data freshness, but the reporting nature is unambiguous.

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 dense sentences with no filler. The core action comes first and the use case follows immediately, so the most important content is front-loaded.

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?

It lists the concrete measures returned (attempts, wall-clock, gate runs, commits, who did them) and the failure-inclusive gate history, which is enough for a single-id query without an output schema. The notable gap is the behavior when no id is supplied, since id is optional in the schema.

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?

The single id parameter is 100% covered by the schema ('One item, with its per-attempt detail'). The description reinforces 'per item' and gate history but adds no new parameter-level meaning 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?

Opens with 'What work has ACTUALLY been done, aggregated from the event log', giving a concrete resource and scope. It enumerates returned measures (attempts, wall-clock, gate runs, commits, actors), so an agent knows what the tool reports, though it doesn't explicitly name a sibling to distinguish from.

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?

Gives explicit intended questions: 'how much effort has gone into this' and an item's full gate history including non-pass outcomes. It does not state when not to use it or point to alternatives, so exclusions are left to inference.

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