WIPE Around

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered; the description adds the one trait annotations can't express — the return format is Markdown. That is meaningful for an agent with no output schema, though it says nothing about error behavior for a missing slug.

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?

Two sentences, front-loaded with what is returned and ending with the one input rule. The content enumeration is long but each listed field earns its place by signalling completeness of the record; minor trimming of 'and more' would tighten it.

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?

For a single-parameter read tool with full annotation coverage and no output schema, the description supplies the two things structured fields cannot: the output medium (Markdown) and the breadth of returned fields. Nothing needed to call it correctly is 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 baseline is 3, but the description goes beyond the schema's terse 'Its slug, or its page address' by giving the concrete acceptable form 'around.iw.pe/b/…'. That clarifies the dual identifier formats rather than merely repeating them.

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 states a specific resource and scope: 'Everything ... about one business,' set against the sibling 'search_businesses,' so the one-vs-many distinction is unambiguous by name alone. It also enumerates the returned content domains (trade, town, address, phone, hours, services with prices), leaving no doubt what kind of record this fetches.

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 tells the agent what to pass and where that value comes from ('from search_businesses'), which establishes the intended search-then-fetch workflow. It stops short of an explicit when-not (e.g. don't use for lookups by name) or naming fallback behavior when the slug is unknown.

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

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

Annotations already establish a safe read-only, idempotent, open-world operation, and the description goes well beyond them: it discloses the ranking factors, the ~25 km radius behavior, availability semantics, the review provenance rule, and the relaxation behavior (a no-result 'when' filter is dropped and query.relaxed includes it). This is unusually rich behavioral context.

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 first sentence is well front-loaded, but the body is a very long, rambling paragraph with nested parentheticals and repeated restatements of the same ranking/filtering rules. The information is valuable but poorly condensed and hard to scan.

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?

For a complex ranked search tool with no output schema, it explains what results contain (page, phone, WhatsApp, prices, booking link, first free time), how they are ordered, and edge cases like relaxation. It is close to complete, though the density makes it hard to verify nothing important was lost.

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 already high (88%), so baseline would be 3, but the description adds real meaning beyond the schema – notably the distinction that Hebrew words trigger parsing/reordering whereas max/when are filters, and that lat/lng only apply when both are given and lie in/near Israel. Some redundancy with the schema remains.

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 ('Search WIPE Around's map of Israel's local businesses') with the covered categories listed, so the agent knows it is a discovery/search tool. It does not explicitly name or contrast with the sibling get_business, but the verb 'search' versus a detail lookup is reasonably inferable.

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?

Gives concrete when/how guidance: write in plain Hebrew to have town/trade/budget/time parsed from words, or use city/kind/max/when in English, plus the key rule that budget/time in words reorder while max/when filter. It lacks an explicit statement of when to prefer this over the sibling get_business.

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