fx_scan_params

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

With no annotations provided, the description takes the full burden of behavioral disclosure. It explicitly discloses the side effect that it 'briefly writes and restores every parameter's value during the sweep' and warns about longer execution on plugins with many parameters. It also discloses caching behavior. This is excellent transparency, though it could mention whether failures leave state unchanged, but the disclosed side effects are sufficient.

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 description is fairly lengthy, but every section adds value: purpose, usage, scope, behavioral notes, and argument definitions. It is front-loaded with the primary purpose and usage, and the structure (paragraphs for scope and behavior, then Args) is logical. The length is justified by the need to convey nuanced usage boundaries and side effects; nothing is redundant.

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?

Given the tool's complexity and that it has no output schema, the description covers all necessary aspects: purpose, scope, when to use, parameter types, behavioral side effects, caching, and references a spec doc for deeper reasoning. While it doesn't describe the return format in detail, it implies what the output contains ('what range/units this specific parameter actually uses'), which is sufficient for an agent to gauge whether to call it. The description is complete for decision-making and invocation.

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 input schema has 0% description coverage, so the description must fully compensate. It does: the 'Args' section clearly specifies both parameters—'track_index: 0-based track index' and 'fx_index: 0-based FX chain index'—providing the exact semantics an agent needs to invoke the tool correctly.

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 clearly states the verb (sweep) and resource (plugin's parameters), and specifies the exact purpose: learning real ranges, units, and curve shapes. It explicitly differentiates this tool from sibling fx_get_params and warns against routine use, making it unambiguous what the tool does and does not do.

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 description provides explicit when-to-use criteria ('when you're genuinely unsure and about to guess', 'only when that reasoning genuinely isn't enough') and clear when-not-to-use guidance (not routinely or proactively). It names the sibling fx_get_params as the alternative and clarifies why this tool is deliberately separate. It even points to a spec doc for the reasoning behind the scope.

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