Run calibration test

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

Annotations already declare readOnlyHint=false, openWorldHint=true and idempotentHint=false, so the description correctly doesn't need to restate safety. It adds real value beyond them: the tool invokes local inference (nontrivial compute) and writes sidecar metrics to a specific directory, which are not derivable from annotations.

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?

Four short sentences, front-loaded with the action and side effect, with no filler. The final sentence restates return fields already covered by the output schema, a minor redundancy that keeps it off a 5.

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 annotations, a full-coverage schema, and an output schema present, the description covers the essentials: what runs, where results land, and which sibling to use instead. Only the practical cost/latency implications of triggering local inference are left implicit.

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%, so category and model_id are already fully documented, including the 'omit to use the first installed model' default behavior. The description adds no syntax, valid-range, or interplay detail beyond what the schema provides, so the baseline 3 applies.

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 resource ('Run heuristic calibration prompts against a Local AI model') plus the persistence side effect (~/.msty-admin). It also explicitly distinguishes itself from the sibling evaluate_response_quality, so an agent can route between them without opening a schema.

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 names the alternative tool and the condition that selects it ('to score a single reply without calling the model'), which is clear routing guidance. It stops short of stating when not to run this tool (cost, latency, prerequisites for a local model), so it falls just below the full 5.

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