ScrapeMole Search

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

With readOnly/openWorld/idempotent already declared, the description still adds substantial behavior: primary Bing News RSS with automatic retry on empty pages, Brave News fallback, source named in the response, 404-not-charged on empty results, and x402 USDC payment terms with a PaymentRequired object when unpaid. That is exactly the runtime context annotations cannot carry.

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?

Dense but front-loaded: usage triggers first, then return shape, then parameter hints, then source/error/payment details. Nearly every sentence carries load, though the long single-paragraph run-on structure slightly hurts scannability.

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 6-parameter, no-output-schema tool, the description covers return fields (title, direct URL, publisher, ISO timestamp, snippet, image), result limits, source and fallback behavior, empty-result handling, and billing. An agent has everything needed to call and interpret it correctly.

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 baseline is 3; the description largely restates sort/freshness/market values already documented in the schema. It adds minor framing (market selects regional editions, freshness limits article age) but omits page/count and offers no new syntax 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?

The description states a specific verb and resource — news search returning articles — and enumerates concrete use cases (current events, press monitoring, recent coverage, digests). The title frames it against web search and autocomplete, but the description itself never names the sibling tools, so differentiation relies on the title.

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 gives four clear triggers for when to use this tool (current events, monitoring, pre-answer coverage checks, digest building), which is strong positive guidance. It stops short of naming when NOT to use it or routing to the web/suggest siblings for non-article queries.

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 only cover read-only/open-world/idempotent, but the description goes well beyond them: primary vs fallback source behavior, source named in the response, 404-and-not-charged on empty results, per-call pricing, and the PaymentRequired flow when called unpaid. That is exactly the operational context an agent needs before invoking a paid tool.

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?

Front-loaded with the primary use case and dense throughout – pricing, fallback, and error behavior all earn their place. It is a single run-on paragraph with stacked parentheticals, which slightly hurts scannability but not content value.

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 two-parameter tool with no output schema, the description covers ordering of results, source fallback, failure semantics, and billing, leaving no ambiguity about what happens on invocation.

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 adds value by enumerating example lang values (en, de, fr, es, ja) beyond the schema's generic 'two-letter language code', though it adds nothing new for q.

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 verb+resource (returns search autocomplete suggestions) and explicitly positions it against the sibling tools by naming /v1/web and /v1/news as downstream consumers. An agent can distinguish suggest from web/news without opening any schema.

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 gives concrete use cases (keyword research, SEO ideas, query expansion, topic guessing) and explicitly states where it fits relative to alternatives ('before /v1/web or /v1/news'), so the when-to-use decision is unambiguous.

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?

Far exceeds the readOnly/openWorld/idempotent annotations: it discloses the source-routing rule (top 10 from Bing RSS, deeper results count>10 or page>1 from Brave), the fallback chain to Mwmbl, the disclosure fields in the response (source, sourceUrl, fallbackFrom), the 404-without-charge error semantics, and the paid x402 USDC pricing with the PaymentRequired handshake. These are non-obvious behaviors an agent cannot infer from the schema.

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?

Use case, return shape, source routing, operators, fallback, pairing, and payment are all front-loaded and each sentence carries information. The payment/error clauses are packed into a single dense run-on, which slightly hurts scanability, but there is no filler or repetition.

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 return-value burden and does so fully: fields returned, how the winning source is identified, and how empty results surface. Combined with the fallback and pricing behavior, nothing material needed to call this 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 description coverage is 100%, so the baseline is 3, and the description adds real meaning on top: it ties count/page to which engine answers (Bing for the first 10, Brave for deeper pages) and documents the supported q operators (site:, "exact phrase", -exclude, filetype:). It leaves market/safe/count semantics to the schema, which already covers them adequately.

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 concrete verb+resource ('search the web') and enumerates the jobs it serves (research, fact finding, finding official pages/docs, competitor or link discovery, grounding with URLs). It states the return unit precisely (ranked organic results with position, title, url, domain, snippet). Scope within the ScrapeMole family ('Web search (SERP results)' vs news and suggest) is clear enough for an agent to route correctly.

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?

Explicit when-to-use framing ('Use when an agent needs to search the web: research, fact finding...'), plus an explicit follow-on partner ('Pair with ScrapeMole Reader /v1/read to turn a result URL into Markdown') and the fallback conditions under which the tool silently switches engines. An agent has enough to decide to call this and what to do with the output.

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