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

Annotations already cover the safe-read profile (readOnly, idempotent, non-destructive, closed-world), and the description goes well beyond them: menu-match ranking puts menu matches first, results cap at 25, demo/test pages are excluded, matched_items carries up to 5 items with id/name/price, and food-truck matches come from the full catalog with a menu_note caveat plus the per-stop caveat. These are behavioral traits an agent could not infer from the annotations.

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?

The description is long but dense and front-loaded: purpose first, then filters, then matching/ranking behavior, then return shape. Every sentence carries information, though the middle menu-matching clause is run-on and could be tightened.

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 full burden and does so: it explains the result shape (up to 25 matches, subdomain as the cross-tool identifier, matched_items fields) plus edge cases (demo/test exclusion, food-truck catalog vs. per-stop menus). Nothing an agent needs to call this correctly appears missing.

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 semantics the schema lacks: the query is matched word-by-word in any order against business name, headline, type, and active menu items (name, description, tags, category). That goes meaningfully beyond the per-parameter examples in 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+resource ("Searches real local businesses on Shortlist Pass") and enumerates the concrete domain (food trucks, restaurants, shops, HOAs). It also distinguishes this discovery tool from the sibling get_business/get_menu tools by noting the returned subdomain is the identifier the other tools take, so an agent can tell where this fits in the workflow.

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?

It clearly states the optional filter dimensions (town, category, query) and what the query matches, and it links results to downstream tools via the subdomain identifier. It does not, however, name an alternative tool or state when NOT to use this search (e.g., when you already have a subdomain, use get_business instead), so the routing guidance is clear but not exclusionary.

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