ScrapeMole Companies

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

Annotations cover read-only/idempotent/open-world safety, but the description adds substantial value beyond them: it discloses the exclusion of forms 3/4/5/144/13D/13G, the inclusion of the 10 most recent filings, the full field set, and crucially the paid x402 USDC payment flow with the PaymentRequired behavior on unpaid calls. That payment detail is essential and not in 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?

A single dense sentence is front-loaded with the use case, then the return payload, exclusions, and payment terms. It is information-rich and well ordered, though the long parenthetical field list is heavy and 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?

Given no output schema, the description compensates by enumerating returned fields and the filings links, and it explains the payment model. It is nearly complete for a no-required-param profile lookup, with only minor gaps such as error behavior for unknown tickers.

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% and provides the cik/ticker examples, so the schema is largely self-sufficient. The description adds the semantic rule that the tool resolves either a ticker or CIK interchangeably ('resolves a ticker or CIK'), which clarifies the either/or relationship beyond the 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 ('resolves a ticker or CIK and returns the EDGAR profile') and enumerates the returned fields, distinguishing it from siblings filings, financials, and search. The title and description make the scope unambiguous.

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 opening 'Use when you need the official facts about a US-listed or SEC-registered company' gives clear usage context, and the exclusion of insider/beneficial-owner forms is explicit. However, it does not directly name siblings (e.g., 'use financials for X') to route the agent among alternatives.

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 by disclosing ordering (newest first), a result ceiling (~1000), form-type exclusions, the exact return fields, and the paid-call mechanics (x402 USDC on Base, $0.002 per successful call, PaymentRequired object returned when unpaid). The pricing and payment-handshake behavior is critical context no annotation conveys.

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 the 'Use when' trigger, then packs output shape, exclusions, and payment terms into compact clauses with no filler. Dense but each clause carries information an agent needs; only the long enumeration of return fields slightly strains readability.

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 enumerating the returned fields (filing date, period of report, accession number, 8-K item codes, size, primary-document and index URLs). Combined with the filtering, exclusion, and payment details, an agent has everything needed to call 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%, so every parameter (cik, ticker, forms, limit, since) is already documented, and the description's form-type and date filtering largely restates that. Baseline 3 applies since the description adds the default form set context but no new syntax or format guidance.

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 ('lists the company's recent EDGAR filings') plus the exact scope (newest first, up to ~1000, filtered by form type and date). It is clearly distinguishable from siblings company, financials, and search because it is explicitly about the filings list rather than a profile or financial statements.

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?

'Use when you need to find a company's annual report, latest quarterly report, recent 8-K events or registration statements' gives concrete triggering scenarios, and the insider/beneficial-owner exclusion (3/4/5/144/13D/13G) tells the agent when this tool will not return what it wants. It stops short of naming which sibling to use instead for those excluded forms.

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 cover read/idempotent/open-world, but the description adds substantial behavior: values are 'as filed (not adjusted)', the precise depth (5 fiscal years, 4 quarters), audit provenance fields, latest shares outstanding, and the full payment model ($0.004 USDC on Base, unpaid calls return a PaymentRequired object). That last detail is exactly the kind of precondition an agent cannot get from structured fields.

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 a usage clause, then the return shape, then pricing — a logical order with no filler. The second sentence is a dense run-on covering metrics, periods and audit fields in one breath, which costs a little readability.

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 carries the full burden of describing returns, and it does: metric count, value history windows, provenance fields and the extra shares-outstanding datum. Combined with the payment precondition, an agent has everything needed to invoke and interpret the call.

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 value by defining the default universe ('13 standard metrics', plus latest shares outstanding) that the vague `metrics` schema text ('Comma-separated subset ... Default all') does not quantify. It still doesn't list the accepted metric identifiers, so it isn't fully additive.

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 concrete verb and resource ('pulls the company's XBRL facts from SEC EDGAR') and enumerates the exact payload (13 US GAAP metrics with values, units, periods, form, accession). The phrase 'without scraping filings' explicitly separates it from the sibling `filings` 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?

'Use when you need a public company's reported numbers without scraping filings' gives a clear triggering condition and implicitly routes the agent away from the filings sibling. It does not name `company` or `search` as alternatives or state when this tool is the wrong choice, so it stops 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, and openWorld, so safety is covered. The description adds substantial behavior beyond that: the match ordering (exact ticker first, then ticker prefix, then name words), the 25-result ceiling, the paid x402 USDC-on-Base pricing at $0.001 per successful call, and the critical detail that an unpaid call returns a PaymentRequired object rather than an error.

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?

It is a single, front-loaded sentence that leads with the usage condition, and every clause (matching order, result cap, payment model, PaymentRequired response) carries unique information. It is dense and long, but not 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 two-parameter, no-output-schema tool, the description covers trigger, matching behavior, result volume, and the unusual payment handshake, which is what an agent needs to invoke it correctly. It stops short of naming the returned fields (ticker, CIK, company name), which the agent must infer, but that is 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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning about how the q parameter is interpreted — matching against SEC's official ticker list with exact-ticker prioritization before prefix and name-word matching. The limit cap is restated but the matching semantics are information the schema does not carry.

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 specific verb and resource — searching SEC's official ticker list (NYSE, Nasdaq, OTC, CBOE; ~10,000 companies) to resolve a name or partial ticker to an exact ticker and CIK. It explicitly frames itself as the step preceding financials or filings lookups, which cleanly separates it from the sibling tools company, filings, and financials.

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?

Opens with a precise trigger: 'Use when you have a company name (or partial ticker) and need its exact ticker and SEC CIK before looking up financials or filings.' That states both the condition for using this tool and the follow-on tools, so the agent knows exactly when this is and isn't the right call.

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