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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false, so the safety profile is covered. The description adds genuine behavior beyond that: results are capped ("up to 10 listings"), each includes type, price as listed, distance, features and a deep link, and the platform cannot transact bookings. The only gap is that it doesn't mention the default result count or pagination/broadening behavior when few listings match.

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 with the core capability front-loaded, followed by result shape and then the booking constraint. Every sentence carries information, though "For daily, monthly or hourly parking" is partly redundant with the sort enum and could have been folded into a sentence about sorting.

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?

With seven parameters and no output schema, the description correctly compensates by describing the return payload (fields plus a listing link) and the up-to-10 cap. Given the tool is a read-only search with full annotation coverage, little else is strictly required; the main omission is any hint about defaults or how to widen a sparse result set.

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 57%, with place, country, features and radius_km self-documented in the schema. The description adds almost nothing at the parameter level — it never mentions sort, limit, space_type or features, and the only oblique hint is "up to 10 listings" versus a limit default of 5. It also doesn't explain that features are conjunctive or what "price as listed" means across the cheapest_* sort modes, both of which are left entirely to the schema.

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 opens with a specific verb and resource set: "Find parking spaces, garages, driveways and car parks listed on Parksy near a place." That is far more informative than the title alone and implies the search-vs-detail split with the get_listing sibling. It stops short of naming get_listing or parking_guides as the alternative, so sibling differentiation is only implicit.

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 by "near a place" and "For daily, monthly or hourly parking," which tells the agent the rental horizons this search supports. The booking caveat ("Parksy does not take bookings: people contact the parking provider") usefully signals what the agent must do after searching. However, there is no explicit guidance on when to use this versus get_listing or parking_guides, and no when-not condition.

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