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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds substantial non-obvious behavior: unknown glacier status is excluded by glacier filters, coordinates constrain peaks rather than trailheads, transport matches documented prose rather than confirmed operation, and historical season text is not a current operating confirmation. These are exactly the caveats an agent needs to avoid over-claiming results.

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?

Purpose and the 'SAME route' constraint are front-loaded, followed by pagination and scope caveats in a sensible order. It is dense and slightly run-on by the end ('Historical season and public transport descriptions are not current operating confirmations' repeats the transport caveat), but nearly every sentence carries distinct information.

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 12-param open-world search with an output schema (so return shape needn't be described), the definition covers pagination, filter semantics, and the key trust caveats about transport and season data. Missing pieces are minor: no guidance on how month or query interact with results, and no note on default limit behavior.

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?

With only 25% schema coverage across 12 params, the description carries real weight and does so for the tricky ones: glacier unknown-exclusion semantics, bbox/near applying to peaks not trailheads, publicTransport meaning documented-not-confirmed, computed round-trip hours, and cursor via nextCursor. Opaque params like month, query, countries, and maxDifficulty get no added meaning, leaving gaps, but the highest-risk semantics are covered.

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?

Opens with a specific verb+resource: 'Find routes satisfying all supplied constraints on the SAME route', and immediately enumerates the filterable dimensions (difficulty, glacier travel, style, round-trip hours). It implicitly differentiates from search_peaks by scoping to routes, though it never names a sibling tool explicitly, and 'Searches all candidate peaks' slightly muddies the object of the search.

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 concrete operational guidance: 'use nextCursor until null for complete results' and 'Read route details and conflicts before recommending', which routes the agent to get_route afterwards. It also flags scope traps ('Coordinates filter peak locations, not trailheads'). It stops short of explicitly contrasting when to use this versus search or search_peaks, so no exclusions of alternatives are stated.

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