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

Annotations already cover read-only, idempotent, closed-world, but the description adds genuinely new behavioral facts: every field carries its source, addresses/coordinates/hours/websites/photos are deliberately excluded, and callers must follow the place url for them. It also discloses that open_now only honours owner-supplied or official-site hours and that none are recorded yet, which prevents a wasted filter call.

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 sentences, capability first, then output limitations, then the open_now caveat — well front-loaded with no filler. The 'ranked like https://knowchelsea.com/best/{category}' phrasing leans on an external URL an agent cannot resolve, which slightly muddies otherwise tight prose.

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 7 all-optional parameters and no output schema, the description carries the burden of explaining results, and it does: sources attached, excluded fields enumerated, and a redirect to the per-place url. What it omits is the actual shape of a returned record and any paging model beyond limit, so the agent still learns the result structure only at call time.

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 the baseline is 3. The description still adds meaning beyond the schema by explaining that open_now is effectively inert with current data and by characterizing the ranking order (the site's best-of list), neither of which is stated in the property definitions.

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 ('Filter curated Chelsea places') and enumerates the filter dimensions (category, sub-zone, tags, featured picks, text), which is far more than a restatement of the name. It does not name any sibling (list_places, nearby_places, get_place) to delineate the boundary, so the agent must infer that filtering-by-facet is the differentiator.

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 context is implied by the filter list and the caveat that open_now currently matches nothing, which steers the agent away from that flag. There is no explicit when-to-use/when-not guidance and no routing to nearby_places or list_places, so the choice among siblings is left to inference.

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