SerpKite

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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds genuine context beyond them: per-call credit costs, the cost difference between depths, and that failed answers are free. It stops short of describing the answer payload's shape or failure modes beyond billing.

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, front-loaded with purpose, then depth behavior and cost. Every clause carries information an agent needs (cost, defaults, failure billing); no 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?

For an 8-parameter, no-output-schema tool, the description covers the core decision (depth) and cost model, which is what most agents need. Gaps remain around the output format of the cited answer and how time/country/language filters affect results.

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 50%, and the description usefully explains the two undocumented depth enum values and ties num_sources to depth=standard. However, time, country, language, exclude_domains, and the interaction between depth and num_sources limits remain unaddressed, so compensation is partial.

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 (answer a question) and resource (live Google results) plus the output form (numbered citations). This is clearly distinct from siblings like search, research, or extract, which return raw results rather than a synthesized cited answer.

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?

Explicitly frames the depth choice: fast answers from the result page for 3 credits, standard reads top pages for 8 credits at 3 sources. That is real selection guidance, but it doesn't say when to prefer this tool over search/research siblings or when to avoid it.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is fully covered without the description. The description's one contribution is "0.5 credit," which discloses a cost/consumption trait not present in the annotations, but it says nothing about rate limits, response shape, or what the suggestions represent.

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 short fragments with zero filler; the purpose statement is front-loaded ahead of the cost note. It is terse to the point of under-specification, but no sentence 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?

For a simple 3-parameter read tool with full schema coverage and complete safety annotations, the description is minimally sufficient. Gaps remain: it never explains that suggestions are derived from the q prefix, how country/language shape results, or whether the 0.5 credit is per-call, but none of these are strictly required given the schema and annotations.

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%, with q ("Search query"), country ("Country code... shared proxy routes") and language ("Does not change country") all documented in the schema. The description adds no parameter meaning beyond that, 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?

"Query suggestions" names the resource (suggestions) but supplies no verb and no scope; it reads as a fragment rather than a statement of what the tool does. An agent can infer this is an autocomplete-style endpoint, but the description does not explicitly distinguish it from the sibling search tool that returns results rather than suggestions.

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 when-to-use guidance, no mention of the sibling tools (search, maps, news) it complements, and no prerequisites or exclusions. The only extra text, "0.5 credit," is a cost note, not usage guidance.

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 behavior beyond the annotations: async execution, robots.txt compliance, sitemap following, Markdown page output, relevance ordering when query is set, and a credit model where limit credits are reserved and the remainder refunded. That cost/reservation detail is the kind of operational context annotations do not cover.

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, front-loaded with the core action, then the query/async behavior, then the return-and-cost contract. No 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?

For a 7-parameter async job tool with no output schema, the description covers the essentials an agent needs: async nature, the task-id handoff to crawl_result, content format, crawl rules, and the credit/limit economics.

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 does enrich query (relevance-first ordering) and limit (credit reservation/refund economics), but adds nothing about exclude_paths/include_paths or max_tokens beyond their schema text.

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+scope: 'Start an async crawl of one website', with concrete mechanics (links to max_depth hops, sitemaps, robots.txt, Markdown). This distinguishes it from map/extract/webpage siblings that don't recursively follow links.

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 operating context: it is async, returns a task id, and explicitly routes the agent to crawl_result to collect results, plus cost semantics for choosing a limit. It does not, however, state when to prefer crawl over map or extract.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered by structured data. The description adds one genuine behavioral fact not in the annotations -- that the call is 'Free' -- which is useful cost context, but it says nothing about whether an incomplete crawl returns partial pages or how the status is reported.

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 short sentence, front-loaded with the action and resource, with the prerequisite attached rather than buried. Every clause carries information and nothing is padded.

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 one-required-param read tool with no output schema, the description covers the essential who/what but omits how to interpret the two return modes (status vs pages) and whether repeated calls are needed to get final results. Adequate but thin, and the trailing 'Free.' is unexplained context.

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 0% for the single 'id' parameter, and the description only implicitly identifies it as the crawl id via 'a crawl started with crawl'. It does not state the format of that id or where it comes from in the crawl response.

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 (Get) and resource (status or pages of a crawl), and ties it to the sibling tool that produces the resource ('started with crawl'), so an agent can place it in the workflow. The 'status or the pages' phrasing leaves slight ambiguity about whether this returns two distinct shapes without naming them.

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 prerequisite ('crawl started with crawl') implies when to call it, but there is no explicit guidance on polling cadence, what to do while the crawl is still running, or when not to use it. Usage is inferable rather than stated.

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?

Goes well beyond the readOnly/idempotent/openWorld annotations with a concrete cost model (1 credit per URL, +4 for summary, +4 for output_schema), a refund policy for failed URLs and failed AI steps, and a timeout consequence ('slower ones are reported as failed'). This is exactly the operational context annotations cannot express.

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, no filler, with the core capability front-loaded and pricing last. Every clause carries information an agent needs for budgeting or parameter selection.

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?

Covers capability, modes, limits, and cost for a 9-parameter tool with a nested JSON Schema parameter and no output schema. Minor gaps (per-page failure reporting shape, interaction of max_tokens with highlights) are handled acceptably by the schema descriptions.

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 89%, so the baseline is 3; the description earns an extra point by explaining the coupling between query and highlights (ranked passages vs full page) and the role of output_schema, which is the non-obvious interaction an agent must get right. Prompt, country, timeout, and max_tokens are left to the schema and are adequately documented there.

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 (read) and resource (URLs, HTML or PDF) plus the output format (clean Markdown) and a hard limit of 20. This is immediately distinguishable from retrieval siblings like search, crawl, or webpage, which fetch or index rather than convert URLs to Markdown.

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?

Explicitly maps three mode combinations to outcomes: query + highlights yields ranked passages, summary yields a short summary, output_schema yields structured JSON. It does not state when to prefer this over the webpage or crawl siblings, so routing guidance is good but not exhaustive.

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/idempotent/non-destructive, so the bar is lower; the description adds genuinely new behavioral facts — up-to-100 images per page, page 2 starting at result 101, and a cost of 1 credit per page. It stops short of describing result ordering or failure behavior when an engine is unavailable.

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 short sentences: capability first, then pagination mechanics, then cost. No filler and nothing buried.

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 an 11-parameter read-only search tool with no output schema, the description covers what is returned, how paging works, and what it costs, with annotations and a 91%-covered schema handling safety and filters. It could mention the engine fallback and date/domain filtering as first-class capabilities rather than leaving them entirely to the schema.

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 91%, and the one undocumented parameter in the schema (page, which has no description) is precisely what the description explains by defining page size and the offset of page 2. That is real added meaning over the schema, though nothing is said about the filter 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?

States a specific verb and resource ("Search Google Images") and even enumerates the returned fields (image URL, size, title, source page), which lets an agent distinguish it from videos, news, shopping and search 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?

Usage is implied by the name and the returned-field list, but there is no explicit statement of when to pick this over siblings such as search/videos/shopping, nor any exclusions. The pagination and credit notes are operational, not selection guidance.

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 safety (readOnly, idempotent, non-destructive), so the description's job is extra context — and it delivers cost ('1 credit; free when nothing is found') and mechanism (sitemaps + start page links), which tells the agent the result set is bounded by what the site exposes. It doesn't mention pagination or result ordering beyond the optional search ranking.

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 short sentences, both front-loaded: the scope and data source come first, the credit caveat second. No filler or restatement of the title.

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, single-required-parameter tool with no output schema, the description conveys what is returned (URLs), where they come from, and the billing model. The only real gap is the unexplained limit parameter and how results are ordered absent a search phrase.

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 60%, with search, exclude_paths and include_paths self-documented in the schema. The description reinforces the search-ranking behavior but adds nothing for 'limit' (cap 5000) or the path-filter regexes, so it does not fully compensate for the documented gap.

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 ('List a website's URLs') plus a precise scope: sitemaps plus the start page's links. That distinguishes it from navigation-style siblings like search or webpage, though it never names crawl, which is the nearest alternative for follow-up content fetching.

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?

'Optionally ranked by a search phrase' implies a discovery use case, but the description never states when to use map versus crawl, search, or extract, and gives no exclusions. The agent must infer the routing decision from sibling names alone.

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, idempotent, openWorld and non-destructive, so the bar is lower; the description still adds real context by disclosing the cost ('1 credit') and the engine-specific caveat that Yandex results carry an oid usable by the place tool. It does not discuss result caps or the page limit, which the schema only implies.

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 the place-tool boundary are front-loaded in the first clause, with operational hints following. The parenthetical field list is dense but each item carries information; nothing is 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 no output schema, the description compensates by naming the fields returned (name, rating, category, address, phone, website, place_id/cid/oid, coordinates) and the cost. Remaining gap is pagination/result-count behavior for a 7-parameter, page-bounded search.

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 86% so the 3 baseline is already met; the description goes further by explaining the q vs location vs ll split (area text vs exact-point viewport) and the engine=yandex/oid relationship, which the schema does not fully spell out. It adds no detail on page or country/language interaction.

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+resource ('Find places') and enumerates the returned fields, then explicitly contrasts itself with the sibling 'place' tool that returns one place's hours and full listing. An agent can distinguish maps from place and search without opening a 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 concrete routing rules: put the area in location (with example values) or in q, and use ll when searching around an exact point; also points to the 'place' tool for single-place detail and names engine=yandex for Russia/CIS. No explicit when-not-to-use exclusions beyond the place-tool redirect, which keeps it 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 declare readOnly, idempotent, openWorld, and non-destructive, so safety is covered. The description adds the useful cost signal ("1 credit"), but says nothing about result volume, pagination depth, freshness defaults, or how the engine fallback behaves at runtime — all relevant for a 12-param 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?

Two short sentences, front-loaded with the action and resource, with the credit cost isolated so it can be scanned independently. No filler or restatement of the tool name.

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 12 parameters and no output schema, the description leaves the agent guessing at the shape of results (titles, sources, dates, URLs) and whether paging is meaningful given the page maximum of 10. The schema carries parameter meaning well, so this is adequate but not complete.

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 92%, so nearly every parameter (including the domain include/boost/exclude semantics and the engine fallback list) is already documented in the schema. The description adds no parameter guidance beyond the schema, which is the correct baseline of 3 when coverage is this high.

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 Google News") and scopes it to recent articles, which distinguishes it from the general `search` sibling by name. It stops short of explicitly contrasting itself with `search`, `scholar`, or `webpage`, so the agent has to infer the boundary.

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?

No guidance on when to pick this over the many sibling search tools (search, scholar, images, shopping, videos), and no note on when a news-specific search is appropriate versus a general web search. The only added context is cost ("1 credit"), which is pricing, not usage selection.

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, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered structurally. The description's one genuine addition is the '1 credit' cost disclosure, but it says nothing about pagination limits, rate limiting, or result volume.

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 fragments, zero filler, and the core purpose leads ahead of the cost note. It is efficient, though the extreme brevity edges toward under-specification rather than disciplined conciseness.

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 a rich annotation set and mostly documented parameters, the essentials are present, and the credit cost is a useful operational detail. Missing are result shape and behaviour notes (e.g. how country and language interact, what happens at page 10) for a four-parameter search tool with no output schema.

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 75%, with country and language explained in the schema and page bounded by min/max, so the schema carries most of the load. The description adds no parameter meaning of its own, making the baseline 3 appropriate.

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 gives a clear verb+resource ('Search patents'), so an agent immediately knows the domain. It does not distinguish itself from near-neighbours like scholar, news, or general search, which is the one thing missing for a top score.

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 when-to-use guidance and no named alternative; an agent must infer that this is for patent literature rather than scholarly papers (scholar) or general web results (search). The only context offered is the cost note, which does not help routing between siblings.

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, idempotent, open-world, non-destructive behavior, and the description adds a genuinely useful cost disclosure ('1 credit; free when no place matches') plus the shape of the payload. It stops short of auth requirements or rate-limit context, but the billing rule is real added value beyond 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?

Front-loaded with the primary identifier and purpose, followed by the return fields and cost. One dense sentence with little waste, though the field enumeration is long enough to be slightly unwieldy.

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 listing the returned fields, and the credit note plus the 'free when no place matches' case hint at empty results. Nothing critical is missing for a zero-required-param read tool, aside from guidance on obtaining the identifier.

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 each identifier and its role is already documented in the schema. The description reinforces that place_id/cid/fid/oid are alternatives and notes oid routes to Yandex Maps, but adds little syntax or constraint detail beyond the schema, matching the baseline for full coverage.

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: fetching the full listing of one place by identifier (place_id/cid/fid/oid). The returned field set (address, hours, rating, photos, etc.) makes the scope concrete and distinguishes it from search-oriented siblings like maps/map, though no sibling is named explicitly.

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 rather than stated: the identifiers are said to come 'from a maps result' or 'a Yandex Maps result', which sketches a workflow but never tells the agent when to pick this over maps/map or what to do when the identifier is unknown. No exclusions or alternatives are named.

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, idempotency and destructiveness, so the description's extra value is cost and timing: it discloses credit pricing per effort tier and that charges only apply when the report is written. It also flags the async behavior and the returned identifier, though nothing is said about duration or failure/cancellation behavior.

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 clauses with zero filler: what it does, how to retrieve the result, and what it costs. The action and the next step are both front-loaded.

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, no-output-schema tool, the description supplies everything needed to invoke it correctly and to continue the workflow via research_result. The cost-per-tier detail closes the only real gap left by the schema.

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 50% with 'input' documented in the schema and 'effort' left as a bare enum. The description compensates by mapping lite/standard/deep to concrete credit costs (30/75/200), which gives the agent real decision-relevant meaning for the undocumented parameter.

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 ('Start an async deep-research task') and enumerates what the task actually does: planned web searches, page reading, and a cited Markdown report written by Claude. That detail clearly separates it from siblings like search, answer, or crawl.

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?

Explicitly says it returns a task id and to 'call research_result with it', which is a clear follow-up path. It does not explicitly state when to prefer this over the 'answer' sibling or quick search, but the 'deep-research task' framing implies the heavy-weight case.

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, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds two pieces of real behavioral value: the call may return either a status or a final report, and it is free to call. It omits polling guidance (how often, whether status values are terminal) and what the response 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?

One compact sentence that front-loads the verb and resource. The trailing "Free." is a fragment but earns its place by disclosing a cost trait that affects whether an agent calls repeatedly.

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 burden of describing returns; it does say status-or-report, which is the essential shape. It stops short of explaining how to tell which one you got back or what to do while the task is still running, which matters for a polling-style 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 0% and the lone `id` parameter has no description at all. The description indirectly compensates by tying the id to a task "started with research", but it does not state whether it is the task id returned by research, whether it is URL-safe, or what form it takes.

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 (get) and resource (status or report of a research task) and ties the resource to the sibling that creates it (research). It does not explicitly distinguish itself from crawl_result, the other *_result sibling, so an agent must infer the pairing.

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?

"started with research" implies the prerequisite and the timing (call after kicking off a research task), which is genuine usage context. However, there is no explicit statement of when not to use it, nor a named alternative for crawl-based result retrieval.

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, idempotent, openWorld, non-destructive, so the safety profile is covered. The '1 credit' disclosure is genuinely useful cost/pricing context beyond the annotations. No mention of rate limits or result shape, so not 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?

Two dense sentences, front-loaded with what the tool returns, followed by the cost. Nothing 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?

Covers purpose and cost, but for a search tool with pagination (page max 10) and optional locale params, the description doesn't clarify pagination behavior or proxy-based country routing. No output schema exists, so the description could say more about result format. Adequate but with clear 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 coverage is 75%, with q, country, and language described in the schema; page has no schema description. The description adds no parameter details, but with high coverage the baseline of 3 is appropriate. The agent learns nothing from the description it cannot get from 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 (search) and resource (academic papers) plus the added value (citations and PDF links), which distinguishes it from the generic 'search' and other vertical siblings. It doesn't explicitly name a sibling it is NOT, so it stops short of 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?

The mention of citations and PDF links implies academic use, but there is no explicit when-to-use guidance vs the sibling 'search' or 'patents', and no exclusions or prerequisites. Usage is only inferable.

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, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuine value beyond that by disclosing the credit cost and the output shape (Markdown with named sections), but it says nothing about rate limits, pagination semantics, or what happens when Google is unavailable with the default engine.

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 short sentences with zero waste: the action first, then the return shape and cost. Nothing is buried and nothing is 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?

For a 16-parameter tool with no output schema, the description adequately covers what is returned (named result sections, Markdown) and the base cost, while the rich schema covers parameter behavior. The main residual gap is that engine fallback behavior and multi-credit combinations are left entirely to the schema rather than being framed at the definition level.

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 94%, so the schema already documents nearly every parameter, including the engine list and cost implications of num/include_answer/include_content. The description only restates baseline cost ('1 credit'), which the schema partially duplicates for the paid options; baseline 3 is correct 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 ('Search Google') and enumerates exactly what comes back (organic results, answer box, knowledge graph, People-also-ask, related searches) as Markdown. That makes it distinguishable from news/images/scholar/videos siblings, though it never names those siblings explicitly.

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?

No statement about when to choose this over the 18 sibling tools (news, images, scholar, maps, answer, research) and no prerequisites or exclusions. The only guidance-adjacent content is a cost note ('1 credit'), which informs budget but not tool selection.

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, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context: the cost ("1 credit") and the shape of the payload (prices and merchants), neither of which appears in the structured fields. It does not cover pagination limits or result-count behavior, so it is not a full 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?

Two short sentences with zero filler, and the core purpose is front-loaded before the cost note. Every clause carries 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 simple read-only search with no output schema, the description conveys both the result content (products, prices, merchants) and the credit cost, which is what an agent needs to select and budget the call. It omits any note on pagination (page max 10) or result volume, leaving a minor 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 80%, so the schema already documents q, country, language, and location; the description adds nothing about any parameter. This is the baseline case where the structured 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 ("Search products") plus the distinguishing content axes (prices, merchants), which separates it from generic siblings like search, news, or images. It does not explicitly name or contrast against any sibling, 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?

There is no when-to-use guidance, no statement of when to prefer this over the plain "search" sibling, and no mention of prerequisites or limitations. The only implicit signal is the word "products," which the agent must infer as the routing rule.

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, idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the safety profile is covered. The description's one addition is cost ("1 credit"), which is genuinely useful billing context not present in annotations, but it says nothing about result volume, pagination limits, or latency.

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 short sentences with zero padding and the purpose front-loaded. However, the brevity crosses into under-specification rather than tightness, since there was room to add routing guidance without bloat.

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 10 parameters, no output schema, and several nuances (engine fallback, date and domain filtering interplay, country vs. language), the description leaves the agent reliant entirely on the schema. It does not explain what a result contains or how credits scale with paging, so it is thin for a tool of this complexity.

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 90%, so nearly every parameter is already documented in the schema, including engine fallback semantics and domain filter formats. The description adds nothing about parameters, which is acceptable at this coverage level but earns only the baseline.

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?

"Search videos" is a clear verb+resource and, because siblings include images, news, scholar, and shopping, the media type alone distinguishes it from most alternatives. It stops short of naming the closest sibling (search) or clarifying that results are video-specific listings.

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 gives no when-to-use or when-not-to-use guidance. An agent must infer from the name alone whether to choose this over search, news, or images, and there is no mention of engine selection tradeoffs (e.g., using auto as a fallback), even though the schema exposes that option.

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 the safety profile (readOnly, idempotent, openWorld, non-destructive), so the description only needs to add context. It does: it discloses that HTML and PDF inputs are supported, that output is normalized to Markdown with metadata, and that the call costs 1 credit. Error handling, rate limits, and paywall/auth behavior remain undisclosed.

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 short sentences with the operation and output format front-loaded, followed by the cost. No filler; every clause carries information an agent can act on.

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 explaining the return value (clean Markdown plus metadata), and annotations cover the safety profile. For a two-parameter read tool this is largely complete, though it omits failure modes and any note on how it relates to crawl/extract.

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 50%: 'country' is documented in the schema while 'url' is only typed as a URI. The description adds a meaningful constraint on url (must be public, HTML or PDF) but says nothing about the country parameter or its geo-routing purpose. Baseline 3 is appropriate given the mixed coverage.

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 (Fetch) plus the resource (a public URL, HTML or PDF) and the transformation applied (main content returned as clean Markdown with metadata). It is clearly not a search, crawl, or extract tool. It does not, however, explicitly contrast itself with close siblings such as crawl or extract, so it stops short of full sibling differentiation.

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 phrase 'Fetch a public URL' implies the use case (retrieve and read one known page) and the restriction to public, presumably unauthenticated pages. There is no explicit when-to-use vs when-to-use crawl/extract, and no stated exclusions (login walls, paywalls, robots restrictions).

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