research_finish

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

With no annotations, the description carries real weight: it discloses that publishing is conditional on checks passing, that it does not send messages or publish externally, that historical checklist receipts stay readable but cannot substitute for current work, and that an author's own disposition cannot clear audit findings. These are genuine behavioral constraints an agent could not get from the schema.

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?

Length is appropriate and the gating condition is front-loaded, but several sentences are compressed into near-opaque noun stacks ('audit and acceptance bound to the current full artifact'), which costs comprehension without saving much space.

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?

The output schema means return values need not be described, and the preconditions are covered. But for a 4-parameter, zero-coverage schema with no annotations, leaving `task` and `artifact` undefined and the checklist contract only alluded to is a meaningful gap.

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% across 4 parameters, so the description must compensate and only partly does. It defines `message` ('intended user-visible delivery text') and gestures at `checklist` via receipt language, but `task` is never explained and `artifact` is only obliquely referenced through 'current full artifact', with its default of final.md unmentioned.

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 first sentence gives a specific verb pair ('verify report delivery and publish its receipt/terminal state'), which tells an agent this is a completion/gate tool. But 'publish' is later negated ('does not send messages or publish externally'), so the core action is muddied, and nothing distinguishes it explicitly from research_review or research_save beyond a passing reference to evaluation_complete.

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?

It implies preconditions for success ('requires completed independent perspectives, audit and acceptance bound to the current full artifact') and names research_review as the source of evaluation_complete for evaluation tasks. However, it never states plainly when to call this instead of research_review or research_save, leaving the routing decision to inference.

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