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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower, yet the description still adds real value: result ordering by years of operation, the walking-distance default, nationwide coverage, and the data limitation that only geocoded shops are searchable. The one remaining gap is what a returned record looks like.

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?

Two short sentences, front-loaded with the geo anchor and default radius, with no filler. The parenthetical notes are compact and each carries information; only the separate 'nationwide' sentence could be folded in.

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 5-parameter tool with zero schema descriptions and no output schema, the description should cover the untuned knobs (limit, min_years, max radius) and at least sketch the return shape. It covers the core grammar of the call but leaves an agent guessing on result size and field contents.

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 and only partly delivers: it explains lat/lng, the default 800m radius, and that results are filtered/sorted by years of operation. It never explains limit (default 10, max 30), the radius_m range up to 5000, or min_years as a tunable threshold, leaving several parameters undocumented anywhere.

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 gives a specific verb+resource (find restaurants that have been open for a long time) anchored to lat/lng, plus the ranking rule (sorted by years). It clearly differs in character from get_restaurant and list_regions, but never explicitly contrasts itself with the near-identical sibling find_long_running_restaurants, so full sibling differentiation is missing.

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?

Usage is implied rather than stated: it tells you it searches nationwide around a coordinate pair, defaults to 800m (about a 10-minute walk), and only covers shops with map coordinates. There is no explicit 'use this instead of X' routing despite a sibling with an almost identical name, and no when-not guidance.

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