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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint, so the safety profile is covered; the description adds genuinely non-obvious context: it starts one run of the Apify Actor through mcp.apify.com using your own APIFY_TOKEN and your Apify account, and returns run/dataset IDs for paging. The repeated "Read-only" claim is consistent with annotations. It stops short of disclosing run cost or concurrency behavior, 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?

Front-loaded and organized into labeled sections (When to use, Returns, Behavior, Docs), which makes scanning easy. There is minor redundancy and a typo ("full, titles") from the opening list being echoed by the fields enumeration, but no sentence is wasted overall.

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?

A 10-parameter tool with no output schema is well served by the explicit "Returns" paragraph describing one-row-per-result JSON plus run/dataset IDs for paging. The main gap is that all parameters are optional and the description never states what a zero-argument call does or which of the three query inputs is required in practice.

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 (topics, keywords, timeframe, decodeUrls, maxArticles, proxyConfiguration, etc.) is already documented in the schema. The description adds no parameter-level guidance such as which of topics/keywords/topicUrls to prefer or what happens when all are left empty. 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 opens with a specific verb+resource ("Scrape Google News") and then enumerates exactly what fields come back (titles, sources, dates, URLs, images). An agent can tell this apart from the stock/market/archive siblings 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?

"When to use: Use when you need recent Google News articles for a query" gives a clear positive trigger tied to the returned fields. There are no exclusions or alternatives named, but no sibling here overlaps the news-scraping domain, so the omission is low-risk.

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 annotations (readOnly/openWorld/destructive=false), the description discloses that each call triggers one Apify Actor run via the hosted MCP gateway, requires the caller's own APIFY_TOKEN, and consumes the caller's Apify account — useful operational context an agent could not infer from annotations. It restates read-only, which the annotations already cover, and says nothing about credit cost or run duration/rate limits.

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 labeled sections (When to use / Returns / Behavior / Docs) are well organized and front-loaded. However, the entire first block — the title restated plus 'Fast, reliable, and structured for analysis. Ideal for traders, researchers, and data teams' — is promotional filler that adds no selecting or invoking value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Returns are explained (one dataset row per result plus run/dataset IDs for paging), and with no output schema that is necessary and done well. But for a 7-parameter, zero-required tool with redundant URL inputs and a nested proxy object, the description leaves the caller without any input-shaping guidance, which is the main thing missing before invocation.

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

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

Schema description coverage is 100%, so the baseline of 3 applies. The description adds no guidance on the parameter set at all, which is a real gap here: startUrls, targetUrl and targetUrls (self-described as 'optional alias for startUrls') overlap, and nothing tells the agent which to prefer or whether searchQueries can be combined with URLs.

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: fetch live prediction-market data (tickers, categories, prices, volume) from Kalshi.com. That is clearly distinguishable from most siblings, though the opening line is padded with marketing ('Fast & Reliable', 'Ideal for traders, researchers, and data teams') and it never explicitly contrasts itself with the Polymarket scraper sibling.

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?

A dedicated 'When to use' line gives a concrete condition: when you need current Kalshi prices, volumes and categories. It does not state when NOT to use it, nor does it point at alternatives among the sibling scrapers, so it stops short of the full routing guidance a 5 requires.

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 annotations (readOnly, openWorld, non-idempotent, non-destructive), the description discloses that it starts one Apify Actor run via mcp.apify.com, requires the caller's own APIFY_TOKEN, consumes the caller's Apify account quota, and only reads public web data. This auth, billing, and run-lifecycle context is exactly the kind of behavior the 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?

The labeled structure (purpose, When to use, Returns, Behavior, Docs) front-loads the key information and each block carries distinct content. The opening sentence slightly duplicates the title, and the field enumeration is long, but nothing is genuinely 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 explaining the return shape (dataset rows as JSON, plus run and dataset IDs for paging) and the run-based execution model. It stops short of mentioning cost implications of large maxResults or failure behavior, but an agent has enough to call it correctly.

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

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

Schema description coverage is 100%, with enums, defaults, and per-value explanations already present for category, timeRange, leaderboardType, and both boolean toggles. The description only restates the filtering axes ('time range, category, and ranking type') and adds no format or interaction details beyond 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?

The description states a specific verb and resource ('Scrape Polymarket leaderboard rankings with full trader profiles') and enumerates the extracted fields (wallet addresses, P/L, volume, positions, trades, bios, social links). It is clearly distinct from the listed siblings, though it never names an alternative (e.g. the Kalshi scraper) to sharpen that 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?

An explicit 'When to use' line gives the triggering condition: needing Polymarket leaderboard rankings and trader profiles with P/L, volume, and positions. There are no exclusion rules or named alternatives, so an agent knows when to call it but not when to prefer something else.

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, destructiveHint=false and openWorldHint, but the description adds meaningful context beyond them: it starts a run of a specific Apify Actor through the hosted MCP gateway, requires the caller's own APIFY_TOKEN, and consumes the caller's Apify account — cost/auth implications an agent would otherwise not know. It does not disclose latency, run failure modes, or rate limits, 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?

Labeled sections (When to use / Returns / Behavior / Docs) make it easy to scan and the critical scoping info is front-loaded. The 'Built for algorithmic trading systems, AI trading agents, RAG pipelines, and financial research' sentence is pure marketing filler, and the title is repeated verbatim at the start.

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 correctly compensates by explaining the return shape (one row per result) and the run/dataset IDs used for paging a full dataset. For a credential-dependent, run-based scraper it covers the essentials, though it omits what happens on run failure or whether results are truncated on the first page.

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 carries parameter meaning and the baseline is 3. The description's line 'Filter by country, importance, category, and date range' only maps loosely onto four of the eight parameters and adds nothing about interactions (e.g. country vs countries merging, empty-string defaults) beyond what the schema states.

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 ('Extract structured economic calendar events') and enumerates the payload fields (actual, forecast, previous, importance) plus coverage (45+ countries), so an agent knows exactly what it gets. It does not explicitly contrast itself with any sibling, though the sibling list is dominated by unrelated scrapers, so confusion risk is low.

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 a labeled 'When to use' section, but its content largely restates the purpose ('scheduled macro releases with actual vs forecast vs previous values ... by country, importance and date range') rather than stating a genuine decision rule. No when-not-to-use, no alternative tool named, and no guidance on paging the dataset instead of re-running.

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 annotations by disclosing that each call starts a run of the Apify Actor 'publicrecords/calibration-ledger' through mcp.apify.com using the caller's own APIFY_TOKEN and Apify account (a real cost/quota implication). It confirms the operation only reads public web data and mutates nothing on the source site, and explains the return shape plus run/dataset IDs for paging — none of which the annotations convey.

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 restates the title verbatim, and the 'When to use' and 'Returns' paragraphs repeat the error distribution/bias/worst misses list already given in the first paragraph. The auth/Apify and read-only sentences earn their place, but the definition is roughly twice the length it needs to 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?

For a 12-parameter, seven-mode tool with no output schema, the description covers what is returned (dataset rows as structured JSON, plus run/dataset IDs for paging), the auth requirement, the billing/free distinction, and the organizations-only scope. Weakness is mode selection: the seven modes and their required fields are only implicit, so an agent must read the schema carefully to know which fields each mode needs.

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 mode enum itself documents text vs lookup/score/compare, so the description adds no parameter-level meaning beyond a restatement of the text-mode example. Baseline 3 is appropriate when the schema already carries all twelve 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+resource: given a claim from a named institution, it returns that organization's track record (error distribution, intervals, bias, band coverage, worst misses with source links). The scope boundary 'Organizations only, never people' and the concrete source list (IMF, OECD, Fed/FOMC, SPF, ECB SPF, listed issuer) make the resource unambiguous; no sibling tool overlaps this function.

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 'When to use' block gives an explicit trigger: someone cites an institutional forecast and you need to know how accurate that institution has been. It also states a when-not (people are out of scope) and that 'no coverage' is an acceptable honest answer. It does not route between the seven modes, but that guidance lives in the schema's mode description.

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 readOnlyHint/destructiveHint annotations it discloses that the call starts an Apify Actor run through the hosted MCP gateway, requires the user's own APIFY_TOKEN, bills to the user's Apify account, and emits both dataset rows and run/dataset IDs for paging. That is exactly the operational context an agent needs before invoking a metered remote Actor.

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 purpose, then cleanly sectioned into When to use / Returns / Behavior / Docs, so an agent can stop reading early. The opening sentence largely restates the title and the 'Read-only' sentence duplicates the annotation, which is minor waste but not disruptive.

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 29-parameter Actor wrapper with no output schema, the description supplies the return shape, run/dataset IDs, auth and billing model, and a documentation URL. It does not explain how the presets (useCase, monitor) interact or what the dataset columns beyond metadata look like, but the schema covers configuration and the missing gap is not blocking.

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 29 well-documented parameters, so the schema already carries the semantics and a baseline 3 applies. The description adds only a single concrete link to parameters (the 10,000-snapshot / maxResults ceiling) and otherwise leaves enum and preset behavior to the schema, which is acceptable.

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 — searching the Internet Archive's Wayback Machine for historical snapshots of a URL or domain — and states the scope of returned metadata (timestamps, URLs, MIME types, status codes, content hashes) plus the 10,000-snapshot cap. An agent can distinguish this from the sibling scrapers (Kalshi, Polymarket, stock earnings) 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?

It gives an explicit 'When to use' clause with a concrete scenario ("see what a page said on a past date"). It does not name a when-not condition or a comparison to an alternative tool, but the sibling list contains no overlapping historical-archive tool, so the guidance is sufficient for 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true and idempotentHint=false, so the safety profile is carried by structured data. The description adds real value beyond that: it discloses the APIFY_TOKEN auth requirement, that the run executes against the caller's Apify account (billing implication), that maxRows drives cost, and that run/dataset IDs enable paging. The 'Read-only' sentence largely restates the annotation, but the auth, account, and cost disclosures justify above-baseline credit.

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 clearly labelled When to use / Returns / Behavior / Docs sections, with no filler clauses. The title and tagline are duplicated at the start and the read-only remark is redundant with annotations, costing it the top band.

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 optional parameters and no output schema, the description still covers everything an agent needs: what the rows contain, that results are per-row JSON with dataset IDs for paging, the auth/billing model, and the cost lever. Nothing required for a correct first call 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 mode, symbols, maxRows, minBeatRate, includeAnnual and onlyRaisedEstimates are already fully documented in the schema. The description only echoes the concepts (beat frequency, raised/cut forecasts) in prose without adding syntax, units, or edge-case behavior, 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 names a specific verb and resource — analyst EPS estimates vs reported earnings for any US stock, sourced from NASDAQ — and enumerates the concrete content (next-quarter consensus, past actuals, beat/miss percentage, beat frequency, four-week estimate revisions). No sibling tool covers this data, and an agent can tell exactly what it gets 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?

An explicit 'When to use' line states the triggering need (analyst EPS estimates vs reported earnings, beat/miss history, recent revisions). It gives clear positive guidance but names no exclusions or alternative tools, so it stops short of full routing guidance.

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