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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the description is not obligated to cover safety. It still adds real behavior the annotations do not: the output is a skeleton rather than a finished report, and its content is derived from the done receipt, not fetched or recomputed.

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?

Effectively one sentence that front-loads the precondition and then enumerates the output sections. Every clause earns its place; nothing is redundant with the title or schema.

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?

With no output schema, the enumeration of what the skeleton contains is what makes the return value predictable, and the invocation precondition is stated. Only minor gaps remain, such as whether the skeleton is prose or structured text and how it handles missing DoD evidence.

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 100% with a single required 'receipt' string already documented as coming from check_flow_done, so the schema carries the parameter burden and baseline 3 applies. The description reinforces that the receipt is the sole source of the report contents, which slightly clarifies dependency but adds no format or handling detail.

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 and output ('Returns a short final-report skeleton') and enumerates its sections (delivered outcome, proof per DoD item, what was not checked, decisions left to the user, next action). It is clearly distinguishable from 'check_flow_done' because it consumes that tool's receipt rather than performing the check itself.

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?

'Use after check_flow_done' supplies an explicit ordering prerequisite, which is the key selection criterion for a terminal drafting step. No exclusion or alternative path is stated, but for a last-step tool the sequencing constraint is the guidance that matters most.

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