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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine behavior beyond that: weight fallback ('its regular and bold when left out'), italic expanding per weight a family has, and the equivalence to an @import line. It stops short of noting output-format caveats edge cases like what happens when a family lacks a requested weight.

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 use trigger is front-loaded, followed by parameter behavior, the exclusion, and then the return shape — a sensible order with little waste. The middle sentences are run-on and pack weights and italic into dense clauses, but each carries distinct information.

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 an output schema present, the return values needn't be described, yet the description still summarizes the stylesheet link and font-family lines, which helps an agent explain the result to a user. All three parameters receive semantic coverage despite low schema coverage. Only the routing to sibling tools for non-CSS use cases is absent.

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 only 33%, so the description has to compensate, and mostly does: it gives concrete id examples ('lora', 'space-mono'), states the weight range and the default behavior when weights are omitted, and explains italic's per-weight expansion (the italic parameter has no schema description at all). It does not explain the 1-4 family cap rationale or whether id lookups can be resolved via search_fonts.

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 names a specific resource and output: 'one stylesheet link from cdn.onlyfonts.ai' plus 'each family's font-family line with a fallback', which tells an agent exactly what it returns. It separates itself from a font-file download tool ('Not for downloading font files to install on a computer'), though it never positions itself against the sibling get_font or search_fonts by name.

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 gives an explicit use trigger ('when the person wants to use fonts on a web page, in an app or in a design tool that takes CSS') and an explicit exclusion ('Not for downloading font files to install on a computer'). What's missing is a pointer to a sibling alternative for the excluded download case, so it lands just short of a 5.

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