aiworker-data

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

With no annotations provided, the description carries the transparency burden. It discloses that the tool is informational only, mentions the price and payment method, and describes what evidence sources are used and what output is produced.

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

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

The description is a single compact sentence that conveys purpose, output, constraints, and pricing without excessive verbosity. Slight density from including pricing and payment details inline is acceptable and does not harm clarity.

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?

Since there is no output schema, the description adequately explains what the tool will return: verdicts, quoted evidence, and links. It also clarifies the evidence scope (Wikipedia plus up to 5 buyer-supplied URLs), making the tool's behavior sufficiently understandable in 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?

The schema covers all four parameters with 100% coverage. The description adds meaningful semantic context beyond the schema, such as requiring exactly one of text or url, the default max_claims of 5, and the role of sources as additional evidence alongside Wikipedia.

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 clearly states the tool's purpose: extract checkable factual claims from text or URL and verdict each claim against Wikipedia and buyer-supplied sources. It also specifies the output includes verdicts, quoted evidence, and 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?

The description implies use for fact-checking claims, but does not explicitly distinguish when to use this tool versus sibling tools like scrape_markdown or scrape_summary. It gives no direct when-to-use/when-not-to-use guidance beyond the core purpose.

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

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

With no annotations provided, the description carries the behavioral disclosure burden. It discloses the data source (DefiLlama protocol summary), a 5-minute refresh interval, and the $0.01 cost paid via USDC/x402, but it does not state whether the call is read-only, what auth is required, or what happens on invalid slugs. 'Snapshot' implies non-mutating but is not explicit.

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 compact sentences front-load the purpose and data fields, then add operational details (refresh, cost, payment). No filler or redundant repetition of schema 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 single-parameter tool with no output schema, the description covers the main data returned, the source and freshness, and the pricing/payment model. It does not specify return format or error handling, but these are less critical given the simplicity and the enumeration of output fields.

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 slug property already includes its pattern and an example (aave-v3). The tool description only reuses the notion of 'by slug' without adding new meaning about the parameter's possible values or behavior, 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 action (Snapshot) and resource (one DeFi protocol by DefiLlama slug), and enumerates the returned data (TVL by chain, category, 1d/7d change, audits). However, it does not explicitly name or contrast sibling tools such as defi_yields, so differentiation is implicit rather than explicit.

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 conveys usage context by describing the exact data the tool returns and its freshness, implying it is for obtaining a protocol snapshot from DefiLlama. It lacks explicit guidance on when to choose this tool over defi_yields or the scrape_* siblings, and gives no exclusions.

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

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

With no annotations provided, the description must carry the behavioral burden. It adds useful context such as data source, normalization, 5-minute refresh, and per-call cost, but it does not disclose output ordering, default limits, pagination, or rate limits. It is helpful but not complete.

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

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

The description is compact and information-dense, with no filler. The first sentence delivers the core purpose and filters, while the second adds important operational details about freshness and cost. 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?

There is no output schema and no annotations, so the description must explain what the agent gets back and how calling behavior works. It does not mention result fields, ordering, default limits, pagination, or what a zero-filter call returns. For a six-parameter data tool, this is a notable 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 only 33%, so the description must compensate. It does explain five of the six filters conceptually (chain, project, symbol, stablecoin, min TVL) but omits 'limit' and leaves the stablecoin boolean semantics ambiguous. It adds meaning beyond the schema for some params but not all.

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 clearly identifies the resource (DeFi yield pools from DefiLlama) and the key capabilities: normalization and filtering by chain, project, symbol, stablecoin, and min TVL. However, there is no explicit verb like 'get' or 'list', and it does not distinguish itself from the sibling tool defi_protocol.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage through filterable fields but gives no explicit guidance on when to use this tool versus defi_protocol or the scrape tools. There are no stated alternatives, exclusions, or conditions that would help an agent route 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?

With no annotations provided, the description carries the full disclosure burden and does so well: it reveals the call is paid ($0.02/call, USDC via x402), that robots.txt is honoured (so some URLs will fail), and that only public pages are accepted. It stops short of describing failure modes or edge cases like JS-heavy pages that yield no main content.

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 sentences with zero filler: the core function and constraints are front-loaded, and pricing forms a clean second sentence. Every element 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?

For a simple two-parameter tool with no annotations and no output schema, the description covers function, constraints, return shape (title, word count, Markdown), and cost. The main gaps are sibling differentiation and failure behavior, but everything needed to invoke it correctly is present.

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%: url is well described ('absolute https url of a public page') and the description reinforces it with 'buyer-supplied URL'. max_chars has only numeric bounds (500-60000) in the schema, and the description adds no explicit meaning for it beyond implying output-length control.

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 one public web page') and precisely describes the output ('clean Markdown with title and word count'), which differentiates it from the scrape_summary sibling. The parenthetical constraints ('buyer-supplied URL, no login walls, robots.txt honoured') further define the tool's scope without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The constraints clearly define when the tool is usable (public pages only, no login walls, robots.txt-compliant) but only implicitly. There is no explicit statement of when to prefer this tool over scrape_summary or the defi 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?

Despite having no annotations, the description discloses important behavioral details: the summary is generated by an LLM, is capped at 200 words, and the call costs $0.04 paid in USDC over x402. It does not mention failure modes, rate limits, or authentication, but the cost and processing behavior are well covered.

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 sentences with no filler. It front-loads the core functional relationship, then adds the distinguishing summary output, constraints, and pricing all compactly.

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 two-parameter tool, the description plus schema is mostly sufficient. It defines the output elements, cost, and LLM behavior, though it could more explicitly describe the return structure and how max_chars influences processing. No output schema exists, so a small amount of extra output detail would make it fully 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?

The input schema documents url and leaves max_chars with only a range; the description adds no parameter-level meaning. 'Same as /v1/scrape/markdown' only indirectly implies shared parameters and does not explain how max_chars affects the summary or scraping. With only 50% schema description coverage, the description should compensate more but does not.

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 clearly states what the tool does: scrape a page like /v1/scrape/markdown and additionally produce a structured LLM-generated summary, key points, and entities. This differentiates it from sibling scrape_markdown, which presumably returns only 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?

The phrase 'Same as /v1/scrape/markdown plus a structured summary' implies when to choose this tool over scrape_markdown: choose this when a summary and extracted entities are needed. However, it does not explicitly state 'use this when...' or exclude cases, so it stops short of full 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?

With no annotations, the description carries the full burden, and it discloses the price ($0.10 paid in USDC via x402), a key behavioral and financial constraint, plus the exact output components including the fact that a best-fit pool may be absent ('if any'). It omits failure modes and empty-result behavior but covers cost, payment, and the non-mutating nature via the word 'read'.

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

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

The description is a single dense sentence that front-loads the tool's identity and output sections before the cost. The colon-separated list and payment clause are all essential, with no filler words.

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

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

Given six optional parameters and no output schema, the description adequately sketches return structure and cost, but it leaves filter semantics (AND vs OR, optionality of chain) and no-match behavior unspecified. An agent would still need to infer how the optional filters combine to form a valid request.

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 only says 'matching a filter' and adds no detail beyond the schema's per-parameter descriptions, so it doesn't improve semantic understanding of chain, limit, symbol, project, stablecoin, or min_tvl_usd.

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 it is an LLM-written read of DeFiLlama yield pools and enumerates the deliverable sections (verdict, key points, risks, best-fit pool, caveats, pool rows), which makes the tool's function and output clear. It doesn't name a sibling, but 'LLM-written' implicitly separates it from raw data tools like defi_yields.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is for narrative analysis rather than raw scraping or protocol metadata, but it never explicitly states when to prefer it over siblings such as defi_yields or scrape_summary. No exclusions or alternative conditions are provided.

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