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

Goes well beyond the readOnly/idempotent annotations: it discloses that every field carries its source, that addresses, coordinates, hours, websites and photos are deliberately absent so callers must follow the place url, and that ranking mirrors a known site pattern. The open_now caveat — that only owner/official-site hours count and none are recorded yet — is a critical disclosure that the filter currently matches nothing.

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 filtering capability, then data-availability limits, then the open_now caveat. Dense and purposeful, though the middle sentence is a run-on that bundles several exclusions together.

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 optional parameters and no output schema, the description does the needed extra work: it states the ranking model, warns that most contact/location fields are omitted, and flags the open_now dead end. Only minor gaps remain, such as result ordering when no query is supplied and whether any facets combine conjunctively beyond tags.

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 description coverage is 100%, so the schema already explains tags (all-must-match), limit, query, category, featured, open_now and sub_zone. The description adds meaning only for open_now (its data-source restriction and current emptiness) and for result ordering; the remaining parameters get no extra semantics beyond 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?

Opens with a specific verb and resource — 'Filter curated Fulham places' — and enumerates the exact facets (category, sub-zone, tags, featured, text), which tells an agent precisely what this tool does. It does not name any sibling (list_places, nearby_places, get_place), so differentiation from those must be inferred from the facet list rather than stated.

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 plus the instruction to 'follow each place url' for addresses/hours/photos, which hints that this tool is an index rather than a detail lookup. However, no alternative tool is named and no when-not-to-use condition is given (e.g. when to prefer nearby_places or get_place).

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