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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the safety profile is covered. The description adds that behavior branches by language and that before/after byte counts are reported, but it omits the meaningful risk context — e.g. that JS mangling can break name-dependent code or that aggressive HTML collapsing can alter whitespace semantics.

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?

A single front-loaded sentence with no filler; the engine mapping and the reporting behavior are packed in without redundancy.

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 annotations cover safety, so the core is adequate. But for a tool with six parameters at 0% schema coverage and defaults like jsMangle=true and htmlAggressive=false, the description should at least flag that the options materially change output.

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 description coverage is 0% across 6 parameters, so the description carries the full burden and largely fails it. It hints at the engine-to-language mapping but never explains jsMangle, jsCompress, cssLevel, or htmlAggressive, leaving four behavior-changing options undocumented anywhere.

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 (minify) and resource (source code) and names the concrete engines per language — Terser for JS, csso for CSS, a structural pass for HTML. That is enough to distinguish it from image/PDF/SVG compression siblings, though it never explicitly contrasts itself with optimize_svg or compress_image.

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?

No when-to-use guidance and no exclusions. An agent gets no signal about which language modes are safe for production, or that this applies to source text rather than the binary-asset siblings (optimize_svg, compress_image) that sit nearby in the toolset.

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