FastAF

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

Annotations cover the safety profile (readOnly, openWorld, non-destructive), and the description adds genuinely non-obvious behavior: a cost of 10 prepaid credits per successful call, that source links may be Google redirect URLs rather than canonical ones, and that the MCP layer returns a compacted view of results. These are real operational caveats an agent would otherwise not know. Minor gaps remain (failure/error behavior, latency) but the added context is substantial.

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 tight sentences that lead with what is returned, then cover targeting, cost, and the source-link/compact-view caveats. Every clause carries information; phrasing like "JSON text blocks" and "compact view" is slightly jargon-heavy but still load-bearing.

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?

There is no output schema, so the description must characterize returns — and it does, naming the answer text blocks, source references, and the compaction caveat. Cost and redirect-link behavior round out what an agent needs before calling a paid, open-world tool; only failure modes are unaddressed.

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% and both enum parameters (country, language) are self-documenting, establishing a baseline of 3. The description restates that country and language target the answer and that queries are natural-language, but adds no format guidance, defaults, or interaction rules 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?

States a specific verb+resource: it returns Google AI Mode answers as JSON text blocks plus source references, and describes itself as a research/Q&A lookup rather than a raw SERP fetcher. It stops short of explicitly contrasting with sibling search_web, which is the nearest alternative, so the differentiation is inferable but not spelled out.

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?

"Supports natural-language search questions with country and language targeting for research summaries" implies the intended use case (researcher seeking a synthesized answer). There is no explicit when-to-use vs when-not, and no mention of siblings like search_web or search_news, leaving the agent to infer when an AI answer beats raw search results.

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 cover the read-only/open-world safety profile, but the description adds genuinely new behavioral context: a concrete cost of 60 prepaid credits per successful call, a 'public data only' scope limit, and that the MCP layer returns only a compact view of results. Missing only failure/rate-limit behavior to reach 5.

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-loads purpose, then return shape, scope, price, and MCP formatting in tight succession with no filler. Dense but every clause carries information; slightly long in a single sentence but not wasteful.

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 compensates by enumerating returned fields (name, headline, location, public identifier, biography). Input, output, cost, and data-scope constraints are all covered, leaving nothing essential for a correct call.

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 single profile_id parameter is already documented as the identifier from the profile URL. The description adds only a slight clarification that a slug is acceptable, so the schema does most of the work and baseline 3 applies.

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 ('retrieve a person by profile ID or slug') plus the domain ('LinkedIn public profile API'), which cleanly separates it from the sibling search_* tools. An agent knows exactly what this returns without opening the 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?

Gives clear intended context: 'for lead research and profile enrichment', which tells the agent when this tool is appropriate. It does not name alternatives or state when not to use it (e.g., use search_web for discovery), so it falls short of a 5.

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 readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so safety behavior is covered. The description adds useful cost information (1-25 prepaid credits per successful call) and states the actual return format is markdown, but its earlier claims about HTML/links/images and AI extraction conflict with the markdown-only statement and the schema. There is no annotation contradiction.

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 purpose is front-loaded, but the description spends space on unsupported output formats and AI extraction before correcting itself with 'This tool returns markdown.' That redundancy reduces clarity and makes the structure less efficient than it could be.

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?

The schema and annotations are rich, and the description adds cost and return-format context. However, the unsupported format/AI claims create a completeness problem: an agent may expect options that are not present in the schema, even though the final sentence clarifies markdown-only output.

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%, and all five parameters are fully documented in the schema. The description only hints at JavaScript rendering and does not add meaning for premium, max_chars, or challenge_mode beyond what the schema already provides, so the baseline of 3 applies.

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 uses a specific verb and resource, stating that it scrapes a public webpage URL and returns markdown. However, it initially claims conversion to HTML, links, images, and AI extraction/summary, which the schema does not support and which the final sentence partially retracts. The core purpose is clear, but the capability list adds avoidable ambiguity.

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 context for research and RAG use and points to REST for other formats or AI extraction. It does not explicitly say when to use this tool versus sibling search tools such as search_web, nor does it clearly state that it should be used for a known URL rather than discovery.

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 declare readOnly/openWorld/non-destructive, and the description adds real value beyond them: a cost model (1 prepaid credit per successful call), a note that the MCP returns a compact view, and a caveat that ratings/availability appear only 'when available'. It does not explain error or empty-result behavior, so it stops short of a 5.

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?

Core capability and modes are front-loaded in the first sentence, and the cost note is placed where an agent will see it. There is minor filler ('for AI agents', 'MCP returns a compact view of these results') and 'Price: 1 prepaid credits' is grammatically rough, but nothing is wasteful enough to hurt.

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 does partially cover returns (titles, prices, ratings, availability, compact view). However, it is silent on the fact that zero parameters are required, what happens if both asin and query are omitted, result limits, and error/credit-failure behavior — gaps that matter for a paid, open-world 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%, including the mutual-exclusion note on asin/query and the marketplace enum, so the baseline is 3. The description reinforces the two lookup modes and mentions marketplace domain support but adds no syntax, default, or constraint detail 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 (Amazon product search and pricing) and enumerates the two modes: ASIN product details and keyword search results, plus offers and bestsellers. The Amazon scope implicitly separates it from search_ebay/search_walmart/search_shopping, but it never explicitly names those alternatives.

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?

'For ecommerce research' gives a loose context but there is no when-to-use/when-not guidance against the many sibling search tools (search_shopping, search_walmart, search_ebay, search_web). Nothing tells the agent which of these to prefer for a given shopping query.

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 cover the safety profile (readOnly, openWorld, non-destructive), so credit goes to the added context: a concrete cost model ('5 prepaid credits per successful call') and a disclosure that MCP returns only a 'compact view' of results. The mention of 'item URLs' as an input path not present in the schema is a minor inconsistency that could mislead.

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 resource and return fields, which is good, but the single run-on sentence mixes purpose, return shape, use cases, pricing and an MCP caveat. The 'eBay search or item URLs' clause is noise that does not correspond to any actual parameter.

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 usefully enumerates returned fields and qualifies them with 'when available'. Cost per call and the compact-view caveat are exactly the kind of context an agent needs before committing credits. Pagination and the misleading item-URL capability are the remaining gaps.

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 query, domain enum and results limit. The description adds no parameter-level detail such as query syntax, marketplace-specific behavior, or result caps. Baseline 3 applies; the 'item URLs' phrasing arguably misdescribes the input surface.

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 ('eBay product search and item data API') and enumerates the returned fields (titles, prices, condition, shipping, links). It is clearly distinguishable from siblings like search_amazon, search_walmart and search_shopping by naming the marketplace. The 'item URLs' claim is muddled since the schema exposes only a query string, but the core purpose is unambiguous.

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?

'Supports marketplace research and price comparison' implies usage but never states when to pick this over search_shopping or search_amazon, nor any exclusions. An agent must infer that the eBay-specific marketplace is the differentiator. Adequate but with a clear routing gap.

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?

Adds context the annotations don't carry: the 5-prepaid-credit cost per successful call and the caveat that the MCP returns a compact (i.e. truncated) view of results. Safety profile is already covered by readOnlyHint/openWorldHint, so this is solid added value with only return-format detail left implicit.

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 tight sentences with the core noun phrase front-loaded and no filler. The middle clause is slightly run-on (result fields + audience packed into one sentence), but the pricing and compact-view notes earn their space.

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 does the work of enumerating return fields (titles, employers, locations, posting details, application links) and flags the compacted output. What remains unstated — localization behavior of country/language — is covered by the schema, so the definition is nearly complete for a 4-param 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 every parameter is already documented in the schema. The description only loosely gestures at query semantics ('a role, company or location') and adds nothing about country, language, or the results cap. Baseline 3 applies.

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+resource (job search / Google Jobs listings) and names the input dimensions (role, company, location). The Google Jobs framing distinguishes it cleanly from siblings like search_web and search_news, so an agent can pick it without opening the 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?

Gives a clear use case ('hiring research and job discovery'), which is enough to route an agent here for job listings. It stops short of explicit exclusions or naming alternatives such as search_web or get_linkedin_profile.

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?

With annotations already covering read-only, open-world, and non-destructive traits, the description adds valuable context: the output format (article titles, sources, timestamps, URLs, snippets when available), a compact MCP view, and pricing (5 prepaid credits per successful call). It does not mention rate limits or auth, but the annotations lower the bar.

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 front-loaded with the core purpose and then adds relevant details about output and cost. It is efficient overall, though slightly longer than necessary with some repetition of return fields.

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?

Given no output schema exists, the description adequately explains return values and notes the compact view. It covers pricing and usage context, though it does not elaborate on pagination behavior or error handling, which are minor gaps.

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 only reiterates country and language targeting and gives examples for the query parameter, adding little beyond what the schema already provides.

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 clear verb (search) and resource (news) and specifies it returns Google News results for a topic, company, or person. It implicitly distinguishes itself from sibling search tools by focusing on news, but does not explicitly name alternatives like search_web.

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 provides clear context for use cases such as news monitoring and research, and mentions targeting by topic, company, or person. However, it offers no explicit when-to-use guidance versus sibling tools like search_web, nor any exclusions.

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 declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful context beyond annotations: pricing at 5 prepaid credits per successful call, the result fields available, the 'when available' caveat, and that MCP returns a compact view.

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 a single, front-loaded paragraph that quickly states purpose, result content, supported input modes, and pricing. The place_id sentence is the main weak point because it is not merely extraneous but inaccurate relative to the schema.

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 4-parameter search tool with full schema coverage and rich annotations, the description covers cost, result fields, and the compact MCP output. Because there is no output schema, its explanation of returned fields is helpful, though the unsupported place_id mode leaves an accuracy gap.

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 actual parameters are fully documented without help from the description. The description adds no additional parameter syntax or meaning, and its reference to a place_id mode introduces a misleading concept not present 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?

States a clear verb and resource: local business and places search with Google Maps JSON results, and lists the key returned fields. It distinguishes the tool from generic search siblings, but the claim that it supports 'place details by place_id' is not backed by any place_id parameter in the schema, which can confuse an agent about available modes.

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?

The description implies the tool is for local business/place lookups and the schema clarifies the location fallback behavior. However, it gives no explicit guidance on when to choose this over sibling tools such as search_web, nor any when-not-to-use conditions.

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 cover read-only/open-world/non-destructive, but the description adds two things they cannot: a hard cost of 5 prepaid credits per successful call and the caveat that MCP returns a compact view of the full results. It still omits error/failure behavior and what happens to credits on a failed call.

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?

Purpose and result shape are front-loaded, then capabilities, then price, then the compact-view caveat. Dense but every clause carries information; the 'for AI agents' framing is the only near-redundant filler.

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 six parameters, no output schema and no nested objects, the description usefully compensates by listing the returned fields and disclosing cost and truncation. Adequate for correct invocation, though pagination limits and citation-lookup input form remain unstated.

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 every parameter including page, results, year_from/year_to and language is already documented. The description only echoes 'year filters' and 'citation lookup' without adding format or interaction semantics, so the baseline 3 applies.

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+resource ('Academic paper and citation search', 'Google Scholar results as JSON') and enumerates the returned fields, so the domain is unmistakable against generic siblings like search_web or search_news. It does not explicitly name which sibling to prefer over it, so it stops 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?

'Supports topic queries, citation lookup and year filters for literature research' gives clear context for when this tool applies. There are no explicit exclusions or named alternatives (e.g. use search_web for non-academic content), so it is context without routing.

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?

Beyond the readOnly/openWorld annotations, the description discloses two things structured fields don't: a billing cost (10 prepaid credits per successful call) and that the MCP response is a compact/abridged view of full Google Shopping results. The "when available" hedge on ratings also sets expectations. Missing: nothing about how deep pagination goes or what an empty result looks like.

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 compact sentences with the core purpose front-loaded, then capability, then cost and response-shape caveat. No filler, though the first sentence is dense enough that the return-field list could be trimmed since it partly duplicates the outputs an agent will see anyway.

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 read-only, no-output-schema search tool, the description covers what's needed: what it returns, the cost model, that results are compacted, and the two localization axes. Combined with a fully documented five-parameter schema, an agent can call it correctly on the first try.

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 every parameter (query, country, language, page, results) is already documented with types, enums and defaults. The description only restates keyword search and country targeting, adding no syntax, defaults or constraints beyond the schema — baseline 3.

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 names a specific verb and resource — product price comparison / Google Shopping search returning titles, prices, merchants, links and ratings — so an agent knows exactly what it produces. It stops short of differentiating itself from the sibling shopping tools (search_amazon, search_ebay, search_walmart), which is the only thing keeping it from 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?

"Supports keyword search and country targeting for ecommerce research" implies the use case, but there are no explicit when-to-use/when-not conditions and no alternative routed to. With three other shopping-search siblings present, an agent gets no guidance on choosing between them.

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?

Adds substantial context beyond annotations: 5 prepaid credits per successful call (cost/rate-limit info), output shape (JSON search_results with item arrays), and the important caveat that the MCP layer returns a compact view rather than raw results. Annotations already cover readOnly/openWorld, so this is strong additive disclosure.

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, followed by output detail and pricing. No filler, though the 'Walmart product search API for AI agents' framing restates the name somewhat.

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?

No output schema exists, and the description covers return structure, cost, and the compact-view caveat; combined with a fully documented 2-param schema, an agent has enough to call correctly. Missing only explicit pagination/error semantics and when to prefer search_shopping.

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% with both parameters fully documented (query, results with default 10 and max 20), so the description need not compensate. 'search URL' phrasing is slightly loose versus the actual 'query' string parameter, adding no real semantic value. Baseline 3.

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+resource ('retrieve listings from a Walmart search URL') and enumerates what comes back (titles, prices, ratings, availability, seller details). Sibling set includes search_amazon, search_ebay, search_shopping — the Walmart scope makes it trivially distinguishable.

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?

Mentions 'for ecommerce research', implying a research use case, but gives no explicit when-to-use/when-not guidance relative to search_shopping or search_amazon. An agent gets a hint of context but must infer the routing decision itself.

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 declare readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds two genuinely non-structured facts: a cost of 5 prepaid credits per successful call (implying failed calls are free) and that the MCP response is a 'compact view' of the full SERP, warning the agent that results may be trimmed. It does not mention rate limits or result-count ceilings, but the pricing and truncation notes are real added value.

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 resource and output shape, then use cases, then cost – a sensible priority order with no filler. The closing sentence about the 'compact view' is slightly awkwardly placed and would read better folded into the output description, but nothing is wasted.

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 usefully names the returned fields (titles, URLs, snippets, positions) and flags that the MCP view is compact, so an agent knows what to expect back. Pricing is disclosed, which matters for a metered tool. Pagination and the 20-result cap are only in the schema, a minor gap for a five-parameter read 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 description coverage is 100%, so every parameter (query, page, results, country, language) is already documented with types, bounds and enums. The description only restates country/language targeting at a high level and adds no syntax, defaults or interaction rules beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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 ('Google Search results (SERP) for a query') and enumerates the returned fields, which is more precise than the bare title. It distinguishes itself implicitly from vertical siblings like search_news or search_scholar by framing itself as the general organic web search, but never names those alternatives.

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?

Offers use-case framing ('source discovery, fact-finding and research') and mentions country/language targeting for localized sources, which implies when to reach for it. There is no explicit when-not guidance and no pointer to sibling tools such as search_news when the intent is news-specific, so the routing decision is left to inference.

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 cover the read-only, open-world, non-destructive profile, but the description adds real value beyond them: the credit price per successful call and the caveat that MCP returns a 'compact view' of results — both are behaviors an agent could not infer. It omits what happens when a username is not found, so it is not fully complete.

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?

One tight paragraph that front-loads what the tool does, then the return contents, then the exclusion, then cost. Dense with information and free of filler, though the 'API for AI agents' framing is slightly redundant.

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 compensates by enumerating the returned fields (name, handle, biography, follower/following/post counts) and flagging availability caveats. Combined with the cost note and annotations, an agent has everything needed to call this 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% and the schema already documents the at-sign tolerance and the character pattern, so the description adds no parameter-level meaning. Baseline 3 is appropriate when the schema carries the full burden for a single required field.

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 — 'look up a username' on the 'X (Twitter) public profile API' — for a named purpose (audience research, profile enrichment), and explicitly rules out the most likely confusion with 'public profile data, not tweet search'. An agent can tell this apart from the search_* siblings 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?

Gives clear use contexts (audience research, profile enrichment) and an explicit exclusion (not tweet search), which is the main disambiguation an agent needs. It stops short of routing to alternatives such as get_linkedin_profile for a cross-platform enrichment decision, so a 4 rather than a 5.

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 declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so safety is covered. The description adds two genuinely new traits: the cost ('5 prepaid credits per successful call') and the shape of the returned transcript JSON (text, start, duration). The only weakness is the unsupported transcript-by-ID behavior claim.

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 and dense, but the unsupported transcript-by-ID clause is noise, and the trailing 'This tool selects YouTube search.' is a redundant, grammatically odd sentence that earns no place. Removing both would sharpen the definition without losing information.

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 read-only, 4-param search tool with no output schema, the description does supply return shape and pricing, which is good. But it leaves a real ambiguity about whether transcripts are retrievable here versus via youtube_transcript, which matters for calling the right 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% and both enums are documented in-schema, so the schema carries parameter meaning. The description adds no syntax or format detail for query/country/language/results, and its 'by video ID' phrasing introduces confusion rather than meaning about the actual parameters.

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 core verb+resource (find YouTube videos by keyword) is clear, but the description opens by claiming it can 'retrieve timestamped transcript segments by video ID', a mode the schema cannot support (only a free-text 'query' parameter exists). That claim also overlaps with the sibling youtube_transcript, so an agent cannot cleanly tell the two apart from the description alone.

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 a generic use case ('content research and summarization') but never states when to choose this over youtube_transcript or search_web, despite obvious overlap with both siblings. No exclusions or prerequisites are offered beyond the price note.

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 cover read-only, open-world, and non-destructive behavior. The description adds useful context beyond those annotations: it discloses the 5-credit cost per successful call, lists returned fields, and notes that the MCP response is a compact view.

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 front-loaded with the core purpose and then adds only useful details: output fields, cost, and compact MCP return format. There is no redundant restatement of the tool name or schema beyond what helps an agent decide to call 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 two-parameter search tool with annotations and no output schema, the description supplies enough return-value context, cost information, and usage framing for an agent to call it correctly. Nothing critical 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 URL and results parameters are already well documented in the schema. The description mentions Zillow search URLs generally but does not add parameter-level detail beyond what the schema provides.

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: searching Zillow real estate/property listings via Zillow search URLs. It also distinguishes the tool from generic page scraping, so an agent can tell it apart from siblings like scrape_page or search_web.

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 frames the use case as US housing research and implies using this instead of generic page scraping. However, it does not explicitly name alternatives such as search_places or scrape_page, nor does it state when not to use this tool.

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 read-only, non-destructive, open-world behavior, and the description adds genuinely useful context beyond them: a cost of 1 prepaid credit per successful call, the returned payload shape (JSON with text, start, duration), and that output is rendered as compact markdown. It does not cover failure modes or what happens when no transcript exists, which keeps it from a 5.

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 opening sentence is front-loaded and efficient, but the trailing sentence "This tool selects a video transcript and renders compact markdown" is redundant with the earlier return-format sentence and slightly conflicts with the JSON framing. A sentence could be cut without losing information.

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 does well to sketch the return shape, but it leaves two gaps an agent needs: the unbacked keyword-search claim (no corresponding parameter) and no indication of behavior when a transcript is unavailable. Adequate but incomplete for a tool with a misleading capability claim.

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 video_id, language, and country are already fully documented with enums. The description adds nothing about the semantics of language fallback or country selection, so the baseline 3 applies.

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 ("retrieve timestamped transcript segments by video ID") which is clear, but it also claims the tool can "find videos by keyword" while the schema exposes no query/keyword parameter and a sibling named search_youtube clearly owns that job. The dual-purpose framing makes it ambiguous which capability this tool actually provides.

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?

There is no explicit when-to-use guidance and no mention of search_youtube as the alternative for keyword lookups, even though the description implies this tool does search. The only usage-adjacent content is a generic "for content research and summarization" phrase, which does not help an agent choose between this and its siblings.

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