Quietwork Lead Feeds

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

The readOnlyHint annotation already covers the safety profile, so the bar is lower. The description still adds real context beyond it: the tool costs nothing to call ('Free'), and it discloses the accepted payment methods (card/Apple Pay/USDC) plus the pass types covered, which tells the agent what kind of information it will get back.

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 with no filler; the subject (pricing and purchase links) is front-loaded and the trailing 'Free.' answers the cost question an agent would otherwise have to ask.

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, read-only informational tool with no output schema, the description adequately covers what the agent gets and that it is free. A brief note that the response is static reference content rather than live inventory would close the remaining 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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies there is nothing to supply — no account, plan, or pass identifier is needed to retrieve the pricing information.

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 concrete resource — pricing and purchase links for 30-day feed passes and x402 day passes — so an agent immediately knows this is the billing/access-info tool rather than a data feed. It is clearly distinguishable in practice from the sibling feed tools, 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?

Usage is only implied: an agent infers it should call this when a user asks how to buy access or what a pass costs. There is no explicit when-to-use statement, no exclusions, and no named alternative (e.g., a support or docs tool).

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?

The readOnlyHint annotation already establishes this is a safe read. The description adds genuinely useful context beyond that: the cardinality (exactly 9 feeds) and the pricing behavior ('Free'), which matters because a paid buy_info sibling exists. It does not mention auth requirements, pagination, or whether the catalog is static.

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 front-loaded sentence with no filler; the field list is dense but earns its place because no output schema exists to carry that information. Slightly list-like, but nothing 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 zero-parameter listing tool with no output schema, the description covers cardinality, the shape of each entry, and cost, which is most of what an agent needs. The missing piece is the relationship to the sibling fetch/buy tools, which would make the catalog's purpose fully actionable.

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 the baseline is 4. The description's enumeration of returned fields is not parameter documentation, but it does compensate for the absence of an output 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?

The description names the resource concretely ('The 9 public-record lead feeds') and enumerates the attributes returned (key, title, source agency, freshness, volume, license terms, regions, record counts), so an agent knows this is a catalog/listing tool rather than a data-fetch tool. It distinguishes itself implicitly from the *_fresh/*_sample siblings that return actual lead records, though it never states that contrast 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?

There is no explicit when-to-use guidance. The word 'Free' hints at a cost distinction versus the buy_info sibling, but the description never says to call this first to discover dataset keys before invoking the *_fresh or *_sample tools, which is the obvious routing decision for an agent.

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?

The readOnlyHint annotation covers the safety profile, and the description goes beyond it with genuinely useful behavior: a hard cap of up to 300 records, a per-call cost of $0.99 USDC, and the x402/Base payment mechanism required to invoke it. Payment/auth requirement disclosure is exactly the kind of context annotations cannot carry; only the absence of any latency or rate-limit detail keeps it from a 5.

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?

Four short, front-loaded sentences with no filler: feeds first, then filters, then volume, then price. Efficient, though the run-on filter clause is slightly compressed at the cost of 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 does the work of indicating the return shape ('up to 300 records with full details') and the payment prerequisite. Combined with a 75%-documented schema, an agent has nearly everything needed; only the fresh-vs-sample selection rule is missing.

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 75%, so the baseline is 3. The description restates what the schema already documents (region, kind as type text match, days 1-30 default 3) without adding syntax, format, or examples beyond it – e.g. it doesn't clarify that region accepts county, city, or community area.

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 (current records, no delay, from one feed) and enumerates the six available feeds, so the agent knows exactly what data it returns. The '(no delay)' framing implicitly differentiates it from the sibling new_business_leads_sample, though the fresh-vs-sample distinction is never made 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 gives operational parameters (filters, record cap, price) but never states when to use this tool versus new_business_leads_sample or the other fresh/sample sibling pairs. Usage is implied by '(no delay)' rather than stated as guidance or 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 readOnlyHint=true already declaring the safety profile, the description adds real behavioral context beyond the annotations: a 7-day data lag, an up-to-100-record cap, and removal of individuals' names, phones and some street addresses. It does not state pagination or whether truncated results are flagged, but the added disclosure is substantial.

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 sample nature, delay, and free/capped status are front-loaded, and the feed list is dense but each entry adds distinct routing information. The trailing standalone 'Free.' is redundant with the opening 'Free 7-day-delayed sample'.

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 read-only sample tool with no output schema, the description covers the essentials an agent needs: what a feed returns, what PII is stripped, the record cap, and region granularity. Only the days window and any truncation/pagination behavior are left unaddressed.

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 genuinely enriches the feed enum (mapping each key to a state/agency source) and clarifies that region accepts a county, city or Chicago community area, but it never mentions the 'days' parameter or its 1-60 window, leaving one parameter's semantics entirely to 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?

The description gives a specific verb/resource ('free 7-day-delayed sample' from one feed) and enumerates exactly what each feed key returns, so the agent knows it is fetching preview business-lead data. The 'sample' vs. the sibling 'new_business_leads_fresh' is implied by the 7-day delay and free framing, but the alternative is never named, so sibling differentiation 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?

Constraints (free, delayed, PII stripped, capped at 100 records) implicitly signal this is a preview/evaluation call rather than a production data pull, which is useful context. However, it never states when to choose this over new_business_leads_fresh or buy_info, nor any prerequisites or 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?

Annotations only declare readOnlyHint=true, so the description carries extra weight and does add real context: a hard 300-record ceiling and a $0.99 USDC charge per call via x402 on Base. Cost and result-cap disclosure are genuinely useful and go beyond the annotation. It does not explain pagination, batching, or what happens on a failed/aborted 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?

Two tight sentences: the payload scope and field list first, then the cap and price. Nothing is padded and the key constraint arrives early. The field enumeration is dense but appropriate for a data-feed 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?

With no output schema, the description correctly lists the returned fields, plus the record cap and payment model an agent needs before calling. Missing only edge behavior (what happens past 300 records, payment-failure handling, whether ntee filters the batch or is merely returned).

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 (state, ntee) are already documented with format examples. The description restates the state scoping and mentions NTEE as a returned field but adds no filtering syntax or semantics beyond the schema. 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?

Clear specific resource and scope: every organization in the newest monthly IRS batch for a single state, with the returned fields enumerated (EIN, name, city, ZIP, NTEE, subsection, ruling month, foundation type, financials). It does not explicitly distinguish itself from the sibling new_nonprofits_sample, so the fresh/sample split is left implicit even though the title says 'full'.

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?

Gives a clear selection condition for the high-volume case: 'Up to 300 records (use the 30-day feed for more).' That routes the agent to a broader alternative when the cap is insufficient. It stops short of naming any sibling tool or saying when the sample variant is preferable.

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 declare readOnlyHint=true, so the description usefully adds the data provenance (monthly IRS EO BMF extract), the exact sample size (10 organizations), the lookback window (3 months before the newest batch), and the returned field set. It does not mention authoritative freshness or rate limits, but for a read-only sampling tool this is solid supplementary disclosure.

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 front-loaded sentence that leads with the resource and scope before drilling into the payload contents and the 'Free' qualifier. Dense but every clause adds information; it is long, yet nothing is clearly disposable.

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 carries the full return-value burden and does so by listing the aggregate stats, the 10-org sample, the up-to-100 organization records and their fields. Combined with the readOnly annotation, an agent has enough to call it correctly, though the fresh/paid alternative remains unexplained.

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 there is only one parameter ('state', documented as a two-letter code with example TX). The description adds 'for one state', matching the schema, but provides no extra format or constraint detail. Baseline 3 is appropriate when the schema carries the parameter semantics.

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 (new US tax-exempt organizations from the monthly IRS EO BMF extract), a scope (one state), and enumerates exactly what is returned (count, categories, 10-org sample, up to 100 orgs recognized in the prior 3 months with field list). It clearly separates itself from leads/trucking/liquor siblings by resource, but never names its closest relative new_nonprofits_fresh, so the fast/full vs sample distinction 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?

The trailing 'Free' and the 'sample' naming imply this is a preview variant, and the phrase 'for one state' implies the required scoping, but there is no explicit when-to-use or when-not-to-use guidance. The obvious alternative, new_nonprofits_fresh, is not named or routed to, leaving selection to inference.

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 declare readOnlyHint=true, so the description does real work: it discloses the $0.99 USDC x402 (Base) per-call cost and the 300-record cap, both of which materially affect whether and how an agent invokes it. It omits pagination/truncation behavior, so not a 5.

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?

Telegraphic and front-loaded: content description first, then filters, then limits, then price. Nearly every clause earns its place, though the field list ('with phone, address and insurance on file') is a bit listy.

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 3-optional-param read-only fetch with no output schema, the description covers the filters, defaults, record cap, returned fields, and cost. It lacks only detail on how results are shaped or whether the 300 cap truncates silently.

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 all three params are already documented there, including defaults, so the schema does the heavy lifting. The description repeats rather than extends the parameter meaning (no syntax for the comma list beyond the schema, no state validation notes).

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 the resource (current FMCSA events: granted, applied, insurance_lapse) and the returned fields, so an agent knows exactly what data it gets. It does not explicitly distinguish itself from new_trucking_authorities_sample, but the 'fresh' vs 'sample' sibling naming plus the 'up to 300 records' hint largely carries that.

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?

Lists available filters and their defaults, which implies how to narrow a query, but never says when to pick this tool over new_trucking_authorities_sample or why a caller would want fresh vs sample data. Usage is implied rather than guided.

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 declare readOnlyHint=true, so the description usefully adds real behavioral context: a 7-day data lag, PII scrubbing ('Phone and street removed'), a 100-record cap, and zero cost. It stops short of describing pagination or return format.

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?

Five terse fragments, purpose first, then constraints. Every clause carries distinct information (delay, filter, scrubbing, cap, cost) with no padding.

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, no-output-schema tool, the description covers the key agent-relevant traits: lag, PII removal, record limit, and free access. Only the meaning of the 'days' window and the record shape remain unspecified.

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. The description only restates the optional state filter and says nothing about the 'days' window, adding no meaning 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: FMCSA operating authorities granted, with the sample/delay qualifier front-loaded. It distinguishes itself implicitly from new_trucking_authorities_fresh via 'delayed 7 days' and the 'Up to 100 records' cap, but never names the sibling or the distinction 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?

Usage is only implied: 'Free' and 'delayed 7 days' hint that this is the cost-free, lagging alternative to new_trucking_authorities_fresh, but the description never states when to pick one over the other. No exclusions or prerequisites are given.

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 safety profile, but the description adds genuinely useful context beyond them: a 300-record cap and a $0.99 USDC per-call charge via x402 on Base. The paid-call requirement is important pre-invocation information an agent would otherwise not have. It still omits rate-limit or error 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?

Two compact sentences with the resource description front-loaded, followed by filters, cap, and pricing. Every clause carries information; nothing is padding.

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 usefully discloses the record cap and cost, and the filter semantics are covered by the schema. It could say more about the record shape or pagination, but for a simple two-parameter list tool it is largely sufficient.

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 (days, county) are already fully documented in the schema. The description restates the filter ranges without adding syntax or semantics beyond what the schema provides, which is the expected baseline 3.

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: 'Current TABC new license applications and newly issued permits', which is clearly distinct from the sibling sample tool via 'fresh'/'no delay'. It does not explicitly name the sample sibling it contrasts with, so it falls short of full sibling differentiation.

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 lists the available filters and their ranges, implying how to narrow results, but never states when to choose this tool over texas_liquor_licenses_sample or the trucking siblings. Usage is only implied by the 'fresh'/'no delay' framing.

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 readOnlyHint=true already covering the safety profile, the description adds genuinely useful behavioral facts beyond the annotations: a 7-day data lag, removal of phone numbers (PII handling), and a 100-record cap. These are the kinds of traits an agent needs to set expectations, though nothing is said about pagination or what happens when the record cap is hit.

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?

Five short, front-loaded clauses with no filler; the resource and the delay constraint lead. The telegraphic style is efficient, though the run of fragments gives no connective structure between the freshness caveat and the sample limitation.

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 lookup with no output schema, the description covers the essential caveats: delay, PII removal, record cap, and cost. It omits return-field composition and any rate-limit behavior, which is a minor gap given the low tool 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?

Schema description coverage is 100% and the schema already documents both 'days' (1-60, default 14) and 'county' (e.g. Harris). The description only restates that county is optional and adds the record cap; it adds no format or syntax detail, 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 description names a specific resource (new TABC liquor license applications and issued permits in Texas) and a concrete scope (7-day delay, optional county filter), so the agent knows exactly what data this returns. It separates itself from most siblings by the 'sample/free/100 records' framing, though it never explicitly contrasts with texas_liquor_licenses_fresh, so the sibling distinction is only implied.

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 rather than stated: the '7-day delay', 'up to 100 records' and 'free' cues signal this is the low-cost, lower-freshness option versus texas_liquor_licenses_fresh, and 'Optional county filter' clarifies scope reduction. There is no explicit when-to-use/when-not statement or named alternative, so an agent must infer the routing decision.

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 declare readOnlyHint=true, and the description adds substantial context on top: the data refreshes daily, the sample deliberately omits phone numbers and street addresses, the record set expands when a state is supplied, and the full feed sits behind a $99/30-day paywall. It does not state how large the 'small sample' is or whether results are paginated or rate-limited, which is the main remaining gap.

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 signal inventory is front-loaded and the state/no-state branching is stated compactly in two parallel sentences. The trailing '$99 per 30 days. Free.' is promotional but does earn its place by clarifying the tier boundary; the only cost is that the first sentence is a dense run-on list.

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 a free tool, no output schema, and only one optional parameter, the description covers everything the agent needs: what the data is, what fields are intentionally excluded, how the response differs with and without `state`, and what the paid upgrade provides. No critical calling information is missing.

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 the single optional `state` parameter is documented in the schema as a two-letter code. The description goes further by explaining the semantic consequence of omitting it (national and per-state counts only) versus supplying it (counts plus a sample), which is behavior the schema alone does not convey.

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 the concrete resource (daily FMCSA insurance-buying signals) and enumerates the signal types included — suspension notices with deadlines, insurer cancellations, suspended carriers, new authorities without insurance, and renewals 14-60 days out. It is clearly a retrieval/list tool, but it never distinguishes itself from close siblings such as new_trucking_authorities_sample, whose subject matter ('new authorities') explicitly overlaps one of the listed signal categories.

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 state/no-state behavior split and the 'Free' vs '$99 per 30 days' framing, which hints this is the trial tier of a paid feed. There is no explicit 'use this instead of X' routing and buy_info — the obvious purchase path for the full feed — is never named, so the agent must infer the alternative.

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