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

Annotations only declare readOnlyHint and openWorldHint, so the description carries the polling/latency story and does it well, including the 'a job still running at 100s is not stuck' reassurance and the completeness of the finished result. It stops short of describing failure or timeout states, which would matter for a long-running async job.

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, front-loaded with the purpose before the operational guidance. Every sentence carries distinct information (what it checks, poll cadence, expected duration band) with 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 async job-status tool with an output schema, the description covers the poll loop, timing expectations, and result completeness, which is what an agent needs to call it correctly. Missing only edge-case behavior such as failed or expired jobs.

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?

There is only one parameter and schema description coverage is 100%, so the schema already fully documents job_id. The description adds no format, source, or syntax detail beyond the schema, 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?

States a specific verb and resource ('Check a JavaScript-rendering job') and names the tools that create such jobs (`scrape`, `extract`), which helps separate it from sibling operations like search and read_scraped. The only wrinkle is that the input schema attributes job_id to a `run_js` call, which does not appear in the sibling list, slightly muddying which upstream tool it complements.

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 explicit operational guidance: poll again in ~10 seconds while status is 'running', do other work between polls, and no need to fetch results elsewhere because the finished result is returned in full. It also bounds normal job duration (30-150s) so the agent knows when polling is still expected rather than pathological.

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

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

Annotations only declare readOnlyHint=true and openWorldHint=true, so the description carries real extra weight: it discloses that the page is parsed by a model per call, that it costs more than 'scrape', and that the user must approve each run. That approval/cost gate is meaningful context an agent needs before invoking. It stops short of describing failure modes or what happens if selectors/fields aren't found.

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 tightly written sentences, front-loaded with the verb+resource, then the cost/approval constraint, then the routing rule. No filler sentences; every clause earns its place.

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 an output schema present, the description needn't explain return values, and the schema covers params fully. It covers purpose, routing, and the key behavioral gate (cost/approval). The only remaining gap is that it doesn't describe how the returned JSON is shaped or what happens on parse failure, but that is largely covered by the 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 100%, so the schema already documents all four parameters (including the run_js polling caveat and the location country code). The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 is 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?

States a specific verb and resource — 'pull named fields off a page as JSON' — and frames the distinguishing mechanism ('without writing selectors'). It contrasts cleanly against the sibling 'scrape', so an agent can tell the two apart without opening either 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?

Names the alternative ('scrape the page and read it yourself') and gives the exact condition that selects it ('when a page you were going to read anyway would answer the question'), plus the condition for this tool ('when you want the fields themselves, in a shape you can compute on'). This is close to the ideal when/when-not formulation.

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 (readOnlyHint=true, openWorldHint=true), so the bar is lower. The description still adds non-obvious context: the returned parameter list is 'authoritative' and 'more current than any documentation', which tells the agent to trust this call over cached knowledge — a real behavioral trait beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose, then the two-step usage pattern, then the hand-off to scrape_target. Every sentence carries a distinct instruction and there is 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?

An output schema exists, so return-value detail is unnecessary. Given a single optional parameter, full schema coverage, and clear routing to the sibling that executes scrapes, the description supplies everything an agent needs 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 single `endpoint` parameter is already documented in the schema with an example ('scrape/amazon/search') and default null. The description restates the omit-vs-supply behavior, which reinforces but does not extend the schema, so 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?

Starts with a specific verb+resource ('List the scrape endpoints') and immediately adds the second mode ('or describe one of them'). It also names the sibling that performs the actual work ('run the endpoint itself with scrape_target'), so an agent can separate discovery from execution 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?

Explicitly prescribes the workflow: call it before assuming a target has a dedicated scraper, then call again with the endpoint name to learn its parameters. It names the alternative (scrape_target) and the condition that selects it, leaving nothing 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 declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description goes further by disclosing the chunked/paginated access pattern, the early-termination recommendation, and the exact response fields (offset, returned_chars, total_chars, next_offset, eof) — real behavioral context beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight paragraphs: purpose first, then the operating procedure and return shape. Every sentence carries actionable information with 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?

With an output schema present, the return fields need not be enumerated, yet doing so is harmless and reinforces the paging contract. Combined with a 100%-documented input schema and readOnly 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 coverage is 100%, so the baseline is 3. The description adds meaning above the schema by explaining that `offset` starts at 0 and that the next call should use the returned `next_offset`, i.e. the semantics of the offset/length interplay rather than just their types.

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), resource (scraped page chunk), and qualifier (offloaded to disk) that clearly separates it from scrape/search/extract siblings. An agent can tell this is the paging reader for offloaded content, not a network-fetching tool.

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 tells the agent where the required `path` comes from ('a scrape result's `content_offloaded`') and gives a concrete loop protocol (start at 0, follow `next_offset` to `eof`). It adds a useful early-stop heuristic. It does not name alternative tools for the case where content was not offloaded, so it falls short of a full when/when-not map.

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 cover the safety profile (readOnlyHint, openWorldHint), and the description adds substantial behavior beyond them: the anti-bot layer, the content_thin failure signal, run_js returning a job id instead of content because rendering is too slow, and the local-vs-remote large-page handling. This is exactly the operational context an agent needs.

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 purpose and the preferred-over-fetch rationale, then the run_js escalation path, then the large-page caveat. Dense and each paragraph earns its place, though it runs a bit long for a single-URL fetch tool.

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?

An output schema exists, so return values needn't be described, yet the description still covers the two non-obvious return shapes: content_thin and the job-id polling flow, plus the truncated-vs-on-disk large-page outcome. Nothing needed to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% so the baseline is 3, but the description adds real meaning: it explains why run_js exists (client-side rendering), why format defaults to markdown (token cost), and the consequence of setting run_js. device and location are left to the schema, which is acceptable given 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 and resource ('Fetch and read a single URL') with explicit scope including JavaScript-heavy and bot-protected pages. Distinguishes itself from a plain HTTP fetch and from siblings like check_scrape and read_scraped by name.

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 explicit when-to-use ('whenever you have a URL and need what is on it'), when to prefer it over alternatives ('prefer over a built-in fetch'), and a sequenced workflow ('try it without run_js first'). Routing to check_scrape and read_scraped is spelled out with the triggering 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 declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds real behavioral context beyond that: a `run_js` in `params` returns a job id that must be polled, same as `scrape`. It does not cover error modes or how the job id maps to `check_scrape`/`read_scraped`, but the key async trait is disclosed.

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?

Four short sentences, front-loaded with the core action and the sibling distinction, then the workflow, then the async caveat. No filler; every sentence carries operational 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?

An output schema exists, so return values need not be explained, and the description still flags the job-id polling case. Endpoint sourcing, parameter sourcing, and the alternative tool are all covered, leaving nothing an agent needs before calling.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3, and the description goes further by telling the agent not to guess `params` keys and to source them from `list_scrapers(endpoint)`. That discovery guidance is genuine added value for an open `additionalProperties: true` object.

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 — 'call a target-specific scrape endpoint with its own parameters' — and explicitly contrasts itself with the generic `scrape` sibling. An agent can distinguish this from `scrape`, `search`, or `extract` 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 an explicit ordered workflow: look the endpoint up with `list_scrapers()`, read its parameters with `list_scrapers(endpoint)`, then call it here. It also names the alternative (`scrape` for arbitrary URLs) and the condition that selects 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 cover the safety profile (readOnlyHint, openWorldHint), and the description adds real behavioral context beyond them: results are ranked from the perspective of the `location` geography, snippets are truncated and not a substitute for the page, and URLs (including anti-bot-guarded pages) are readable via `scrape`. It stops short of stating rate limits, latency, or query-length constraints, but it is well above the annotation-only 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?

Front-loads purpose, then usage conditions, then output/behavior caveats — a sensible information order. The middle paragraph is slightly long-form with some redundancy ('current events, news, prices' overlapping with 'latest'), but every sentence carries actionable content rather than 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?

An output schema exists, so return-value documentation is not required, yet the description still gives the useful shape (titles, short descriptions, URLs) and warns that snippets are truncated. Combined with explicit sibling routing and geographic caveats, an agent has everything needed to call this correctly and to know what to do next.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds genuine meaning the schema does not: ranking and pricing are resolved for the country in `location` rather than a global average, and unrecognised geo values are silently coerced (documented in the schema too). The query guidance in the schema ('keyword-shaped beats sentence-shaped') is not repeated, which is fine.

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 concrete verb+resource ('Search the live web') and immediately scopes the output ('ranked organic results'). It also draws the line against siblings by naming `scrape` as the follow-up tool for reading page content, so the agent can separate retrieval from reading without opening either 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?

Explicitly enumerates when to use it (current events, prices, availability, versions, 'latest', past-cutoff facts, competitor research) and states the preference over a built-in web search or answering from memory. It also carries a clear negative case: 'Not for local files, git, or anything off the public web.'

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