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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real operational caveats: output should be reviewed before production, the tool is not a full CSS parser, and results should be visually regression-tested. That is material guidance an agent would not get from the structured fields. It stops short of saying exactly which constructs are or are not touched (comments, calc(), strings), which keeps it from a 5.

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 purpose and the review warning before the alternatives. Each sentence carries distinct information (scope, alternative, tool type, return/caveat), though the warning and return sentence could be merged without loss.

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 single-param tool with no output schema, the description covers purpose, alternatives, output type ("compacted CSS source text"), and the key caveat that a full parser is not used. The one gap is not knowing what transformations are applied, which matters for an agent deciding whether the output is safe to ship.

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% and the single `code` parameter is fully documented in the schema, including its 4096-character limit, so the baseline of 3 applies. The description adds no syntax or format detail about the input beyond what the schema already provides.

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+resource ("Conservative CSS minification") with scope qualifiers (small snippets, basic whitespace cleanup) that separate it from the is-minify-js and is-html-minify siblings. The added clarification that this is a transformation tool rather than a boolean validator further distinguishes it from the is-*-safe family.

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 names when to use it (small CSS snippets where basic whitespace cleanup suffices), when not to (complex stylesheets — use a CSS-aware build tool), and the sibling alternative for a different language (is-minify-js). Nothing is left to inference.

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