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

Annotations only declare readOnly/openWorld; the description adds offline operation, data provenance and licensing (GeoNames + DB-IP, CC BY 4.0), the precision ceiling (no street addresses), and — critically — the paid cost of $0.001 via x402. Cost and coverage limits are exactly the behavioral facts an agent must know before invoking.

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 dense sentence front-loads what the tool is and the mode-selection rule, then appends granularity and cost. No filler; every clause carries information (modes, sources, limits, price).

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 7-parameter tool with no output schema, it covers input modes, result granularity, and cost. Minor gaps remain: no statement of what the response looks like or how `limit` defaults/behaves, and no rate-limit note, but the essential call-time facts are present.

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% so each parameter is already documented, but the description adds value the schema lacks: the mutual-exclusivity rule ('exactly one of'), the input->output mapping (ip yields country/region/city/lat,lon), an example query format, and the postcode+country pairing for precision.

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?

Names a specific verb+resource ('offline geocoding') and immediately enumerates the four supported input modes, with the data sources named. It also differentiates scope from siblings by stating granularity ('city/place level; no street addresses'), which separates it from tools like location_report or resolve_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?

Gives clear operational context: use exactly one of ip, q, postcode, or lat+lon, with 'optional country filter' and 'reverse' semantics for lat+lon. It does not, however, name an alternative sibling tool or state when this should be preferred over location_report/resolve_name, so it stops short of full routing guidance.

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