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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds genuinely non-obvious behaviour: results expose which requirements fail or are unconfirmed (pageview caps, PV vs UV, styles chosen at the foundry), that prices are published-only and 'nothing is bought', and that some dimensions are only partially confirmed. It stops short of describing price-source freshness or ranking effects of the goal parameter.

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?

Front-loaded with purpose before caveats, and the closing 'Published prices; nothing is bought' is a well-placed boundary statement. The first sentence is dense and stacks enumeration inside a clause, but nothing is padding for a 14-parameter tool.

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 14 parameters and no output schema, the description carries the return-value burden and does: it says the answer contains per-offer published prices, failing or unconfirmed requirements, and the foundry page. Combined with the covered-fonts boundary and the no-purchase statement, an agent needs nothing more to call it correctly.

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 100%, so every parameter including goal, lang, traffic_metric and medium is already documented in the schema itself, and the baseline is 3. The description restates the input dimensions (users, websites, pageviews/unique visitors, years) but adds no syntax, units or interaction detail beyond the schema.

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 (check which licence a use needs and what it costs) and pins the exact covered corpus: six named offers from Pangram Pangram, Fontwerk, Grilli Type and Fontfabric. It also draws a hard boundary — 'Other typefaces are not covered' — so an agent can separate it from any broader pricing tool without opening the schema.

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?

Gives explicit trigger conditions ('Use this when the user asks whether one of these fonts can be used on a website, on desktop, in print, in an app or game, in a logo or in paid ads') and an explicit exclusion with a fallback behaviour ('say so instead of guessing'). The when-not case is stated as an instruction, not left to inference.

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