SEC EDGAR data

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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses cost ('free, no key needed'), deterministic behavior ('Same steps, same plan_id'), a budget-capped optional AI extraction step marked `assisted` that fires only when no entities are passed, and the degradation path returning three candidates. It even names the output fields (`entities_used`, `missing`, `plan_id`, max price) that an agent would otherwise have to discover by calling.

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 contract is front-loaded and every clause carries information, but it is a single dense paragraph of fragments and colon lists that takes close attention to parse. It is efficient rather than padded, though splitting the entity-trust rule from the cost/execution rules would improve scannability.

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 planner with no output schema, it covers everything an agent needs: what it returns, that it is free and deterministic, how entity passing improves the plan, the assisted-extraction fallback, and how to proceed to paid execution. No structural question is left open before invoking it.

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 real semantic weight: it says to pass the question verbatim *and* extracted entities, explains that the planner trusts the entities over its own parsing, and that they are echoed in `entities_used` with `missing` naming what to add on a re-call. That is behavioral meaning the schema itself cannot express.

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 uses a precise verb+resource combination: it 'turns a question in plain words into the exact typed Bosco Labs calls', listing what the plan contains (tool, input, why, max price, gaps). It explicitly distinguishes itself from the sibling that executes those calls ('Run it with run_official_records_plan (paid, max_usd) or call the listed tools directly'), so an agent can separate planning from execution without opening a 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 names the execution path (run_official_records_plan with max_usd) and the alternative of calling listed tools directly, and states the precedence rule that user-supplied entities beat the planner's own parsing. It also describes the low-confidence fallback (top 3 candidate tools). What it lacks is an explicit 'do not use this when you already know the tool' exclusion, so the routing is clear but not fully bounded.

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 safety profile (readOnly, idempotent, non-destructive, openWorld), so the description only needs to add what they cannot. It does that well: pricing of $0.005 per company-period is a cost signal the agent cannot get from structured fields, and 'Every value cites the XBRL tag and the SEC filing it came from' discloses provenance. It stops short of stating rate limits, pagination, or what occurs on an unresolvable ticker.

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?

Three sentences, capability first, audience second, trust/pricing last, with no filler or marketing padding beyond the brief 'clean' and 'without parsing filings' framing. The price line is separated and easy to scan. Slightly dense in the first sentence, but every clause carries 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 6-parameter read-only retrieval tool with no output schema, the description covers what it returns (income statement, balance sheet, cash flow items with per-value citations) and what it costs. The notable gap is that zero parameters are required, and the description never states that at least one of tickers or ciks is needed or what happens if both are omitted. Pagination and multi-company limits are also unaddressed, but not essential to a first correct 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 every parameter already carries its own documentation with defaults, ranges and enum values; the baseline of 3 applies. The prose adds only light framing ('per fiscal year or per quarter, by ticker or CIK') and one worked metric example, most of which restates schema content. Nothing new is said about interaction between ciks and tickers or about behavior when both are supplied.

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 and resource ('Get clean financial statements of any US-listed company from the SEC's own XBRL data') and enumerates the content dimensions: revenue, profit, EPS, balance sheet, cash flow, FCF and margins. It also states the two retrieval axes (annual vs quarterly, ticker vs CIK), so an agent can tell this is a per-company fundamentals fetch. It never names a sibling, so differentiation from sec_company_screen (which likely also touches financials) is left to inference.

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?

'For analysts, finance apps and AI agents that need a company's numbers over 5-20 years without parsing filings' gives an audience and a motivating scenario, which implies when to reach for this tool. There is no explicit when-not, no prerequisite statement, and no routing guidance versus sec_company_screen or sec_filings_feed. An agent must infer the boundary from the resource nouns alone.

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, idempotent, non-destructive and open-world. The description adds genuinely new behavior: per-row XBRL tag and SEC accession/URL citations, and a stated price of $0.002 per screen-row, which matters because maxResults is billed. It does not describe pagination or result ordering limits beyond the argument docs.

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?

Three short paragraphs: capability plus examples, audience, then provenance and price. Front-loaded with the screening verb, and no sentence is 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?

With eight parameters, no output schema and a per-row charge, the description does the right extra work by disclosing citation behavior and pricing. Only gaps are return cardinality/pagination and any note that results are limited to filers with XBRL data for the given period.

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?

Even though schema coverage is 100% (baseline 3), the description adds concrete meaning on top: it maps natural-language screening intent onto the filter/sortBy/metrics triple ('revenue over $10B and net margin above 20%', 'top 20'). It also frames the crop of metric names as revenue, profit, margins, cash flow and balance sheet, so the agent understands the enum's scope without scanning all 36 values.

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 ('Screen every US company that files with the SEC') scoped to financial metrics, with two concrete query examples. It implies bulk screening versus the single-company sibling sec_company_financials but never names or contrasts that sibling 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?

The example queries ('revenue over $10B and net margin above 20% in 2025', 'top 20 by operating cash flow') and the audience line ('analysts, finance apps and AI agents') imply when the tool fits. There is no explicit when-not guidance or pointer to alternatives such as sec_company_financials for one company or sec_filings_feed for filings.

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, non-destructive and open-world, so the safety profile is covered. The description adds genuinely new context: real-time latency ('filings accepted minutes ago'), full history to 1994, the exact fields returned per row, and a per-filing price of $0.001, which is important cost information an agent cannot get from the schema.

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 action and resource, then scope, then row contents, ending with pricing. It is a single dense sentence carrying a lot of enumeration, which is borderline verbose, but nearly every clause adds usable information; the audience list is the weakest part.

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 9 optional parameters, no output schema, and no required inputs, the description does the necessary work by explaining what a returned row contains (company, CIK, ticker, form, filing date, acceptance time, item codes, links) and how far back data goes. Missing pieces are minor, mainly default sort/pagination behavior and whether empty filters return the whole market.

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 parameter semantics are already fully documented in the structured schema. The description mostly restates those filters in prose, adding only light interpretive value via 8-K item code examples (2.02 earnings, 5.02 officer changes, 1.01 material agreements) that the schema also lists. 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?

States a specific verb (Get) and resource (SEC EDGAR filings as clean JSON), enumerates the form families covered, and gives the scope (one company, watchlist, whole market) and historical depth (back to 1994). It does not, however, distinguish itself from close siblings such as sec_company_financials, sec_insider_trades or esef_annual_reports, so an agent still has 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?

Usage is implied through the scoping options ('for one company, a watchlist or the whole market') and the audience list (investors, news/alert services, compliance teams, AI agents), which hints at freshness-sensitive alerting use cases. There is no explicit when-to-use versus when-not guidance and no named alternative among the 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 readOnly, idempotent, non-destructive and open-world, so safety is covered. The description adds genuine context beyond that: the 2006 coverage horizon, the definition of a cluster (2+ directors/officers, same company, within a window, at least $100,000 combined), and explicit pricing per unit (transaction=9, cluster-signal=100). The only weak spot is that the priced 'unit' concept is never tied to maxResults or includeClusterSignals, leaving a cost-model ambiguity.

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 is front-loaded and information-dense, but the description then stacks a cluster-signal sentence, a filter sentence, an audience sentence ('For investors, fintech apps and AI agents'), and a pricing line. The audience sentence earns nothing, and the malformed pricing markdown adds noise rather than 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?

For a 13-parameter, zero-required, read-only query tool with no output schema, the description does a solid job: it enumerates the returned fields so the agent knows the row shape, and explains the cluster record type. What is missing is how the pagination cap (maxResults 200) relates to 'every' transaction and how billing units accrue, which matter for a paid 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 one of the 13 parameters is already documented with examples and constraints, which sets the baseline at 3. The description does highlight the main filter axes but adds no syntax, precedence, or interaction rules beyond what the schema states (for example, it does not explain dateFrom vs lookbackDays precedence in its own words). It neither compensates for nor undermines 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 and resource: retrieve every insider purchase and sale reported on SEC Form 4 back to 2006, with the exact fields returned spelled out (who, what, when, shares, price, post-holding). It also names a distinctive secondary capability, cluster buy/sell signals, which separates it from generic filing feeds. It never names a sibling like sec_ownership or sec_filings_feed, so the boundary with those tools is left for the agent to infer.

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?

Usage is only implied through the filter list (ticker, CIK, code, role, value, date) and the cluster-signal feature. There is no explicit statement of when to reach for this tool rather than sec_ownership or sec_filings_feed, and no mention of prerequisites or what to do when a query returns nothing. Adequate but with clear gaps for an agent choosing among 27 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 readOnly=true, idempotent=true, openWorld=true, destructive=false, so the safety profile is settled. The description adds genuinely non-structured context: the pricing model ($0.0018 per ownership-row), the fact that each returned row is a charged event, and that 13F results include changes vs the previous quarter. It does not disclose pagination behavior, whether all parameters are optional and which defaults apply, or any rate/row-cap implications beyond the per-row cost.

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 structure is front-loaded: the core question, then a compact enumeration of the four data sources, then the price. There is minor filler ("For investors, analysts and AI agents"). The long single sentence is dense but each clause maps to a distinct mode, so little is wasted.

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 13-parameter, four-mode tool with no required parameters and no output schema, the description covers what data comes back conceptually but not what a returned ownership row looks like or how to page beyond maxResults. It also leaves mode-selection and the insider-sale overlap with sec_insider_trades for the agent to infer. Adequate to get a call made, but not complete for a tool of this complexity.

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?

With schema description coverage at 100%, the schema already documents every one of the 13 parameters including per-mode applicability. The description only reinforces the mode semantics ("13F, with changes vs the previous quarter", "who filed a 5%+ stake") and names example fund/ETF tickers. It adds no syntax or format detail beyond what the schema supplies, 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 gives a concrete framing ("Who owns a stock and who is about to sell it, from official SEC filings") and then enumerates exactly what each form type yields (13F holdings with quarter-over-quarter changes, N-PORT fund/ETF holdings, 13D/13G stakes, Form 144 planned sales). It is far more specific than the title alone. It stops short of naming how it differs from the sibling sec_insider_trades, which overlaps with the Form 144 / insider-selling territory.

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?

Usage is conveyed by example domain (a fund like Berkshire, an ETF like VOO/ARKK, a 5%+ stake filer, an insider filing to sell), which implies when to pick this tool. However, there is no explicit when-not guidance, no mention of the alternative sibling tools, and no statement of how to choose between the four modes at the description level — that choice is left entirely to the schema's mode enum.

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