fastmean_sweep

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

Annotations already declare non-read-only, non-destructive, non-idempotent, closed-world, so the safety bar is partly met; the description adds real value by guaranteeing 'the original schematic is preserved' and noting that native samples and provenance are retained per point, implying N separate owned runs with accumulation cost. It stops short of saying how results are surfaced or whether the sweep returns handles the agent must fetch later.

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 core action and scope, no filler. Minor jargon ('native', 'owned', 'provenance') slightly reduces first-pass comprehension for an agent unfamiliar with the domain.

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 9-parameter tool with no output schema and no schema descriptions, the description omits the result/return path entirely — an agent cannot tell whether the sweep yields inline results (as in fastmean_ac) or run identifiers requiring fastmean_list_runs/fastmean_get_result. It also leaves the 'overrides' vs 'settings' vs 'definitions' distinction, and the role of the 'analysis' enum, unexplained.

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?

With 0% schema description coverage across 9 parameters, the description carries the burden and does clarify the two most ambiguous ones: 'target' accepts either a native variable or a component.parameter, and 'values' is bounded at 1–32. But 'path', 'signals', 'timeout', 'analysis', 'overrides', and 'definitions' get no mention at all, leaving the majority undocumented in both places.

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 — sweep one variable or component.parameter over a bounded value list — which clearly separates it from single-run siblings like fastmean_ac, fastmean_dc, and fastmean_transient. The distinction from fastmean_edit_values/edit_parameters (mutation vs. execution) is implicit rather than stated.

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?

The 1–32 value bound and the 'each point is a separate owned native calculation' line imply 'use this instead of re-running a single analysis N times,' but no explicit when-to-use, when-not-to-use, or named alternative is given. An agent must infer the choice from the siblings list rather than from the description.

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