diana_review_prepare

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

With no annotations, the description carries the full burden and does so well: it discloses that the 3D window switches to a fitted model view, that the panel is modeless and native to DianaIE, exactly what the panel displays, and that neither the MCP nor closing the panel can approve. What it leaves unstated is the call's return timing relative to the user's click and any failure modes, which is a real gap for a human-in-the-loop gate.

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 opening sentence front-loads the purpose, and the paragraph is organized as visible effect, then panel contents, then procedural constraint, then next steps. Dense but each sentence carries information; only the phrase 'the complete analysis .dcf' is slightly opaque.

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 human-in-the-loop gate, the description covers what the user will see, what the agent cannot do, and the exact follow-up sequence, and an output schema exists so return values needn't be described. The only material omission is the meaning and accepted format of the 'analysis' argument.

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 parameter 'analysis' has 0% schema description coverage, so the description must define it, but it never says whether this is an analysis name, an ID, a file path, or a handle to a development-stage calculation. It only implies the analysis must be development-stage, which is a constraint rather than a definition.

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?

States a specific verb and resource ('Prepare a mandatory human review for a development-stage calculation') plus the visible effect ('open it inside DianaIE'). It is clearly distinguishable from diana_review_status, which it names as the follow-up step, and from diana_solve, which it names as the consumer of the result.

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 marks the review as mandatory for development-stage calculations and lays out the exact workflow: call this, then diana_review_status, then pass the approved review_id to diana_solve. It also states that the user, not the MCP, must approve, which sets the precondition for progressing.

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