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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the rejection rule for abbreviations and the reason (postal tables key on full name) — behaviourally useful context an agent cannot infer from the schema.

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?

Three short sentences, front-loaded with the action, then the usage rule, then the rationale. No filler and nothing repeated from the title.

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-parameter enumeration tool with full annotation coverage and no output schema, the description tells an agent what it returns (region names), why they matter, and how to use them. Only the country parameter's value set and default are left implicit.

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%, so the description carries the burden. It conveys that region names are country-scoped, linking the regions to the 'country' parameter, but never explains the parameter's accepted values or its 'us' default — that is left entirely to the enum. Partial compensation only.

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 — list the exact region names a scrape accepts for a country — and adds the crucial qualifier 'accepts', which distinguishes it from generic region lookups and from siblings like list_scrapes or search_categories.

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 clear context for use (fetch the names before submitting a scrape) and the operational rule 'submit them verbatim'. No alternative tool is named, but none of the siblings offer an overlapping capability, so the omission is low-cost.

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