SEC EDGAR Filings (x402)

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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the bar is lower. The description adds free pricing, data provenance (SEC EDGAR public domain), and a verify-at-source/no-warranty disclaimer, but most of that is legal boilerplate rather than call behavior such as response shape or 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?

Short overall, but 'Free.' and 'Price: free.' are redundant, and the sentence fragments read as disclaimer boilerplate rather than front-loaded purpose. Some trimming would help.

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 zero-parameter informational tool with no output schema and annotations covering safety, the description gives enough context to call it correctly and to know what content to expect (pricing, payment network, terms, data source).

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, so there is nothing for the description to disambiguate and the baseline of 4 applies. Schema coverage is 100% and empty by design.

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 resource (this server, tool prices, payment network, terms) and makes clear it is informational. It is easy to distinguish from the sibling data-fetch tools like get_8k_events, though the verb is implicit ('describes').

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?

Implied usage only: an agent can infer it is for learning about the server, pricing, and terms. There is no explicit when-to-use or when-not, and no guidance on calling it before other tools.

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 read-only and idempotency, but the description adds material context the annotations lack: a 20/min rate limit, free-of-charge access, and the upstream source (SEC EDGAR, public domain). The 'extractive only' note also signals that output is verbatim metadata rather than analysis.

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 the resource and its returned fields, followed by operational facts (cost, rate limit). A meaningful share of the tail is boilerplate disclaimer text ('not investment advice', 'Verify at source; as-is, no warranty') that does not help an agent invoke the tool correctly.

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 only two well-documented parameters and no output schema, the field enumeration plus source, cost, and rate-limit notes give an agent nearly everything needed to call it. Missing only a note on what an empty result means (no filings vs. invalid ticker).

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 'days' explicitly documented as default 90 / max 365 and 'ticker' given examples. The description only echoes the day-window semantics ('in the last N days') and adds no syntax, edge-case, or format detail beyond the schema.

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 ('Form 8-K filings for a ticker') and enumerates the returned fields (form, accession number, report date, Item numbers/titles, EDGAR URL). Siblings (get_insider_trades, get_ownership_stakes) cover different filing types, so the resource itself differentiates, but the description never names or contrasts them explicitly.

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?

'Extractive only' and 'in the last N days' imply intended use (retrieving raw filing metadata for a recent window) and warn against expecting summaries. There is no explicit when-to-use/when-not guidance or pointer to any alternative tool for other filing types or time ranges.

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 read-only/idempotent/open-world profile, and the description adds substantial value beyond them: it discloses the paid access mechanism ($0.02 USDC via x402 on Base), the public-domain SEC EDGAR provenance, and explicitly states that footnotes/remarks/addresses are omitted — a meaningful scope limitation for Form 4 data. The as-is/no-warranty/verify-at-source notice further sets expectations about reliability.

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 core scope and returned fields are front-loaded in the opening sentence, with cost, provenance, and disclaimers following in short fragments. The field enumeration is long but each item earns its place by telling the agent what data is present; the disclaimer tail is slightly verbose but defensible for a financial data 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?

There is no output schema, so the description carries the return-value burden itself — and it does so by listing the exact returned fields and the omitted ones. Combined with cost model, data source, and licensing caveats, an agent has everything needed to decide, call, and interpret results for a simple 2-parameter 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%, with both ticker and days (default 90, max 365) fully documented in the schema itself. The description adds only a loose 'last N days' restatement and nothing about ticker formatting or window constraints beyond what the schema provides, 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?

States a specific verb+resource ('Form 4 transactions for a ticker in the last N days') and enumerates the exact fields returned (owner, relationship, transaction date, code, shares, price, shares owned after, accession, EDGAR URL), so an agent knows precisely what it retrieves. The Form 4 framing cleanly separates it from siblings like get_ownership_stakes or get_8k_events without needing to name 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?

The description implies when it is useful (recent insider activity within a look-back window) and clarifies it is informational only, not investment advice, which hints at context. However, it never explicitly states when to prefer this over get_ownership_stakes or get_8k_events, and no exclusions or prerequisites are given despite three relevant 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false. The description adds valuable behavioral context beyond that: price ($0.02 USDC via x402 on Base), omitted narrative/address fields, SEC EDGAR data source, and no-warranty/as-is terms. It still does not discuss rate limits or response-size behavior.

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 front-loaded: it opens with the data resource and scope, then lists returned fields and omissions, then pricing and disclaimers. Every clause adds useful context 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 a two-parameter read-only tool with full schema coverage and clear annotations, the description covers what is returned, what is omitted, data source, pricing, and warranty limits. No output schema exists, and the return fields are sufficiently enumerated for correct 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 coverage is 100%, with both ticker and days fully documented including default and max values. The description mentions ticker and last N days but adds no syntax or format details beyond what the schema already provides, so 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?

The description states a specific resource and scope: SEC Schedule 13D/13G filings for a ticker over the last N days, and lists the returned fields. This clearly distinguishes it from siblings like get_insider_trades and get_8k_events without needing their schemas.

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 by saying it returns filings on a ticker in the last N days, but it does not explicitly say when to use this versus get_insider_trades or other siblings, nor does it state when not to use it. The informational-only disclaimer is not usage guidance.

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