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

The annotations already establish a safe, idempotent, open-world read, so the description's job is to add context, and it does: hard-constraint semantics, the shape of the return (compact summaries, IDs, total, nextOffset), and the important caveat that peak-level filters can describe different routes. It stops short of covering result ordering or what 'compact' omits, so it is strong but not exhaustive.

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 tight sentences: capability first, constraint semantics second, workflow caveat last. No filler, and the most decision-relevant clause (filters are hard constraints) is up front.

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?

An output schema exists, so return values need not be spelled out, yet the description still flags total and nextOffset, which is helpful for pagination. For an 11-parameter search tool with nested bbox/near objects, the only real gap is the absence of any guidance on combining geographic filters with the free-text query.

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 55%, so the description needs to compensate, and it does by naming the filter families (country, elevation, season, difficulty, glacier) and by adding semantics the schema cannot express — that these are hard constraints and that difficulty/elevation are peak-level, not route-level. It is silent on bbox, near, and the query string beyond the family list, but those parameters carry their own schema descriptions.

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?

A concrete verb ('find and compare') plus the resource ('mountains') and a list of the filter dimensions it supports, so the agent knows exactly what it gets. It also names get_peak and get_route as downstream steps, which partially distinguishes it from siblings, but it never explicitly contrasts itself with search or search_routes, leaving the nearest alternatives ambiguous.

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 operating context: all filters are hard constraints and are never silently relaxed, and the agent is told to read get_peak and get_route before recommending a route. That is real routing guidance, though it stops short of stating when this tool should be preferred over search_routes or resolve_peak.

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