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

Annotations already declare readOnly, idempotent, closed-world behavior, so the description's job is to add context beyond that, and it does: it discloses that addresses, coordinates, hours, websites and photos are NOT returned and that the place url must be followed for them, and it flags that open_now data is unpopulated. A minor gap is that ordering/tie-breaking and result-volume behavior beyond the limit parameter are not spelled out.

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, front-loaded with the core purpose and filters, then the return-shape caveat, then the open_now warning. Dense but each sentence earns its place; the middle sentence packs several omissions into one clause, which is efficient rather than padding.

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 no output schema, the description carries the burden of describing returns, and it does so by naming what is included (sourced fields) and what is excluded (addresses, coordinates, hours, websites, photos) plus the follow-up url. It stops short of describing result envelope details like total counts or pagination, which is a small residual gap for a 7-parameter search tool.

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, but the description adds real meaning beyond the schema: the ranking model tied to the category slug and the data-availability caveat on open_now, which no schema field conveys. The 'every tag must match' semantic is already in the schema, so it repeats rather than extends there.

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?

States a specific verb and resource ('Filter curated Notting Hill places') plus the exact dimensions it filters on and the ranking model ('ranked like https://knownottinghill.com/best/{category}'). It never names siblings such as list_places, nearby_places, or compare_places, so an agent must infer the boundary itself, which keeps it short of a 5.

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 the filter list, and there is one useful caveat ('open_now only matches owner-supplied or official-site hours, and none are recorded yet') that effectively tells the agent not to rely on that parameter. However, there is no explicit when-to-use or when-not-to-use guidance versus sibling tools like nearby_places or list_places.

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