NOVA

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

With no annotations, the description carries the full burden and does so: it discloses the $0.99 USDC price, the x402 PaymentRequired result on unpaid calls, and that payment is verified and settled before execution. It also pre-empts surprises by listing refused request classes.

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

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

The purpose is front-loaded in the first sentence, with payment and refusal details following in a logical order. The long enumeration of return fields is dense but each item is decision-relevant; a little trimming of that list would tighten it further.

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

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

There is no output schema, so the description must describe returns itself, and it enumerates the executive answer, cited URLs, claim/evidence matrix, conflicts, confidence, risks, and next actions in both JSON and Markdown. Combined with the payment flow disclosure, an agent has everything needed to invoke and interpret this tool.

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

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

Schema description coverage is 100% and each parameter is documented in the schema (including depth and time_window defaults), so the schema does the heavy lifting. The description only restates the parameter list ('research question plus an optional company, domain, time window, and depth') without adding syntax or semantics beyond it.

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 artifact ('Create a cited research decision memo from public sources') and enumerates the output contents, so the agent knows exactly what it gets. However, it never differentiates itself from the sibling company_intelligence_report, which plausibly overlaps on company-scoped research, leaving the agent 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?

It states the applicable domains ('For business, technical, and general public research') and gives explicit exclusions (private-person dossiers, fabricated citations, restricted scraping, trading signals, automated medical/legal/financial/employment/insurance decisions). This is strong when/when-not guidance, though it never names an alternative tool for the refused cases.

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 does well: it discloses the $0.25 USDC price, that an unpaid call returns an x402 PaymentRequired result and does NOT execute, and that payment is verified and settled before execution. That is exactly the pre-invocation behavior an agent needs. It omits latency, rate limits, and any auth requirements beyond payment.

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 scope, then the payment mechanics in three tight sentences with no filler. Slightly dense on the payment sequence, but every sentence 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, but the description compensates by enumerating the returned sections (profile, offerings, market signals, developments, risks, citations, confidence, diagnostics) and explaining the payment-gated failure mode. An agent has enough to call this correctly and interpret the result.

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 both parameters are already documented in the schema. The description adds no syntax, format, or constraint detail about 'website' or 'focus' beyond what the schema provides, 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 first sentence states a specific verb and resource: 'Create a source-linked company intelligence report from a public company website,' and the second enumerates the report's contents. It is clear what the tool produces, though it never distinguishes itself from the sibling cited_research_brief, which sounds adjacent in 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?

Explicit intended contexts are listed (agent workflows, vendor review, sales research, partnership screening) plus one exclusion ('not for high-stakes automated decisions'), which is genuine when/when-not guidance. It stops short of naming an alternative tool for the excluded case or for overlapping research needs.

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 does disclose the two traits that matter most here: it is free and it does not execute research (no side effects). It also enumerates what the catalog contains, which stands in for return content. It stops short of describing format or size of the catalog.

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, zero filler, with the identity of the tool front-loaded and the cost/no-side-effect guarantee immediately after. 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?

For a parameterless, annotation-free discovery tool with no output schema, the description covers what it returns and its cost/behavioral profile, which is most of what an agent needs. Minor gap: no hint about how to consume the returned example inputs when invoking the paid tools.

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 tool takes zero parameters and the schema confirms an empty object, so there is nothing for the description to disambiguate. Baseline 4 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 resource and contents: a catalog of NOVA MCP tools, USDC prices, and example inputs. That is enough to separate it in kind from the sibling tools (research briefs, intelligence reports, output recovery), though it never explicitly contrasts itself with 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?

'Calling it does not charge and does not run research' clearly signals the intended context: use it to inspect available tools, pricing, and sample inputs without incurring cost or side effects. No explicit exclusions or named alternatives are given, but the cost/side-effect framing makes the when-to-use case clear.

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 does well: it discloses the $0.01 USDC price, that an unpaid call returns an x402 PaymentRequired result and does not execute, and that payment is verified and settled before the tool runs. It also states the deterministic retry-prompt behavior on persistent failure. It stops short of describing the successful return shape or any limits beyond the schema's maxLength.

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 is front-loaded, followed by a compact capability list, use cases, and the payment terms. Every sentence is substantive, though the 'useful for...' list is generic filler that could be trimmed.

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 tool with no annotations, no output schema, and nested parameters, the description covers the operation set, failure path, and payment behavior. It is nearly complete; the main gap is that the successful return value (recovered data plus validation status) is only implied, not described.

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 67%, so the schema documents most parameters. The description reinforces the 'schema' parameter (enforcing a supplied JSON Schema) and the coercion/default options, but it never mentions 'removeAdditional' or adds syntax/format detail beyond the schema. This is the expected baseline when the schema does most of the work.

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 ('Recover and validate broken structured output from LLMs and AI agents') and then enumerates the concrete operations: extracting JSON from prose/Markdown, repairing malformed JSON, enforcing a schema, coercing types, reporting validation errors, and generating a retry prompt. This is unambiguous and self-distinguishing, even though the siblings (research/catalog tools) are unrelated domains.

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 offers usage contexts ('tool calls, agent workflows, automation pipelines, and API integrations'), which are essentially universal and provide no real selection criteria. There is no when-not-to-use guidance and no named alternative, so usage is only implied rather than explicitly framed.

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