FMCSA Carrier Intelligence

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

There are no annotations, so the description carries the full burden. It does disclose two genuinely useful traits: the call is paid, and it returns a single flat row rather than a graph. However, it omits auth/permission requirements, rate or cost specifics, and what the returned counts mean or how to interpret a high/low value, so behavioral coverage is only partial.

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 blocks: the core measurement is front-loaded, and the cost/output note is separated and terse. The nested parenthetical is slightly heavy but every sentence is informative, 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?

With no annotations and no output schema, the description must cover invocation and result interpretation. It does identify the source records and the mailing-address exclusion, and signals a single-row result, but leaves the sole parameter undescribed and does not explain what the counts imply for consistency judgments.

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 0% and there is a single required parameter, usdot_number, which the description never mentions. The schema supplies only type (integer) and required status, so the description should clarify what identifier is expected (USDOT number format) but adds nothing.

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 measurement: a count of distinct business addresses and phones a carrier reports across named FMCSA record sets (census, licensing/insurance, crash records). It also distinguishes itself from sibling identity tools by noting it is cheaper and returns 'one row, no graph,' which tells an agent this is a lightweight consistency count rather than a full identity resolution.

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?

'Paid. Cheaper than either identity tool; one row, no graph' hints at when to prefer this over check_carrier_identity or screen_carrier_identity, but the guidance is comparative and cost-focused rather than a clear when-to-use statement. There is no explicit trigger condition (e.g. 'use this to spot data conflicts before paying for full identity resolution') and no stated 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 no annotations, the description carries the full burden and delivers: exact validation constraints (usdot must not appear in roster, non-empty, max 100 distinct entries), the failure classes and their cost (free invalid_arguments, free not_found), the metered pricing formula, and the reassurance that 'not linked' is a complete billable answer. This is unusually thorough behavioral 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?

Purpose and return shape are front-loaded well, and every sentence carries substance. It is somewhat long and repeats the 'still your own input, not a new disclosure' reassurance and cross-references to sibling conventions multiple times, which is slightly redundant though defensible for a metered 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?

For a 2-parameter tool with no output schema and no annotations, the description covers inputs, return fields, error/edge cases, cost model, and success semantics — nothing an agent needs to call it correctly 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 0% and both parameters are bare integers, so the description must compensate — and it does: usdot_number is 'the applicant', roster_usdot_numbers is 'your own list, supplied by you', plus the constraint that the applicant must not appear in the roster and the roster's size cap. This adds real meaning the schema cannot 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?

States a specific verb and resource ('Screens one applicant carrier against a roster of carriers') and explicitly positions itself as 'the batch generalization of confirm_identity_link', so an agent can distinguish it from siblings without opening any 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?

Gives a concrete use case — catching a carrier previously cut from the network re-entering under a new USDOT number — and names the sibling it generalizes (confirm_identity_link). It stops short of an explicit 'when not to use this / use X instead for single pairs' rule, so the routing is implied rather than fully spelled out.

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?

No annotations exist, so the description carries the full burden and does so unusually well: it discloses billing behavior per outcome, the fact that flagged is FMCSA's ARCHI rule and not a fraud determination, that flagged != match_score >= 1.5, and that score_provenance.match_score_ceiling is computed per carrier and usually caps at 2.5. It also enumerates what the tool deliberately never returns (linked USDOT, legal name, hashes), which prevents an agent from misrepresenting output.

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 and the cheaper alternative are well front-loaded, but the second and third paragraphs are long defensive digressions (why a linked carrier's identity is not the caller's to receive, confirmation from reading Truckin's hashing code) that do not help an agent select or invoke the tool. Substantive content, but several sentences do not earn their place for the invocation decision.

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, no annotations, and a subtle domain (match scoring, flags, ceilings), the description supplies the interpretive context an agent needs: what flagged means, how it differs from the score threshold, why ceilings vary per carrier, and how billing and not_found behave. Nothing essential to calling or interpreting this tool 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?

There is a single integer parameter with 0% schema description coverage, so the description must compensate. It adds behavioral meaning about the parameter's value (an unknown USDOT number yields a free not_found) but never states the expected format, validity range, or what a USDOT number actually is, leaving the semantic gap only partly filled.

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 (full identity-linkage detail for a carrier) and immediately distinguishes itself from the sibling screen_carrier_identity by purpose and price. An agent can tell exactly which of the two identity tools to pick 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?

Explicitly routes the agent: 'Priced meaningfully above the free screen_carrier_identity — call that first if you only need the flag and a count.' It also gives exclusions and edge-case outcomes (a carrier with no linked carriers is a valid, billable answer; an unknown USDOT is a free not_found), which is exactly the when/when-not guidance expected.

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 so richly: privacy guarantees (never discloses identity the caller didn't already have), result semantics (cluster_id returned only when linked), error behavior (invalid_arguments when the two numbers are equal, free; free not_found on unresolved numbers), and pricing behavior (paid, pricier, billed the same for 'not linked').

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 core purpose and the key differentiator, then layers in semantics, routing, and pricing. Every sentence carries real information, though the parenthetical cross-references make it longer than strictly necessary.

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 and no annotations, the description fully covers what an agent needs: return semantics (cluster_id only when linked), error cases and cost, and the alternative tool. Nothing required to invoke it correctly 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 0%, so the description must compensate, and it does: it explains that both usdot_number_a and usdot_number_b are caller-supplied, must differ, and must resolve in carrier_identity_cluster. It does not document the value format, but the behavioral constraints it adds go well beyond the bare titles.

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: it confirms or denies that two specified carriers share an identity cluster. It explicitly distinguishes itself from check_carrier_identity and screen_carrier_identity, so an agent can select it without opening any 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?

Explicit when-to-use: when you ALREADY SUSPECT two carriers are linked, as the lower-risk alternative to the removed linked_carriers field. It names the alternative (check_carrier_identity) and the condition that selects it ('who is linked to this carrier?'), giving clear routing.

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 that the call is free and unauthenticated (no credentials or paid tier required), which is the key behavioral fact for an agent deciding whether it can call it. It omits rate limits and the response shape details, but the safety profile for a discovery call is effectively covered.

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, front-loaded lines: identity, payload, and the imperative call-to-action. No filler, and the most decision-relevant facts (free, unauthenticated) come first.

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 convey the return contents, and it does: tables, fields, pricing, freshness. Combined with the zero-parameter schema, an agent has everything needed to call it correctly; only per-field response detail is left 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?

The tool takes zero parameters, so the baseline is 4 and there are no parameter semantics the description could or should add.

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 concrete verb+resource ('Free, unauthenticated dataset catalog') and enumerates exactly what it returns: every table sold, its fields, current pricing, and freshness. It does not explicitly contrast with siblings, but the siblings (carrier/identity lookups) are unrelated domains, so no disambiguation trap exists.

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?

'Read this before paying for anything' gives an explicit triggering condition and makes the tool the correct first step of a purchase flow. It stops short of naming alternatives or stating when not to call it, but the guidance is directly actionable.

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 behavioral burden and does so for the key traits: it is 'free' and 'unauthenticated,' and returns sample rather than live data. It does not mention rate limits, pagination, or error behavior, but for a zero-param read-only sample tool the cost/auth/no-write disclosure is the substantive part.

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, front-loaded with the free/sample framing. Slight redundancy in restating the check_carrier_identity purchase rationale already implied by naming the sibling, but no meaningful waste.

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 simple no-param sample tool with no annotations and no output schema, the description covers cost, auth, and which response shapes are demonstrated. It could be more complete by listing the fields present in the sample, but the essentials an agent needs to call it are present.

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?

Zero parameters, so the schema is trivial and fully self-documenting (100% coverage). There is nothing for the description to add on parameters, making the baseline of 4 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+resource (get identity sample) and explicitly frames it against two named siblings: it covers both screen_carrier_identity's free IdentityScreen shape and check_carrier_identity's paid IdentityAssessment shape. An agent can tell what this returns and how it relates to the identity-checking siblings without opening any 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?

Gives a clear usage context and the deciding condition: use it to see the paid response shape and evaluate data quality 'before spending USDC on check_carrier_identity.' It names the relevant alternatives, though it doesn't explicitly say when NOT to use it (e.g., vs. the generic get_sample sibling).

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 at all, the description carries the full behavioral burden and does substantial work: it discloses the billing model (charged only when records return, exact-key misses free), the legitimate emptiness of changelog, and precise date-gated null semantics for eight fields. It still omits auth/rate-limit/pagination behavior, so it is strong but not exhaustive.

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, pricing, and caveats are front-loaded in that order, and each sentence carries distinct information about result interpretation. The three consecutive 'null before <date>' enumerations are verbose and could be compressed, keeping it out of 5 territory.

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 rightly spends its budget describing return contents (field-level null semantics, excluded contact fields, changelog exclusions), which is a real strength. But for a two-parameter tool with 0% schema coverage and a required usdot_number plus an unmentioned since_date, the parameter story is incomplete, leaving the definition only adequately complete.

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 0%, so the description must compensate, and it does not: neither usdot_number nor since_date is explained, and the several hard-coded cutoff dates (2026-09-02, -06, -12) are never tied to the since_date filter an agent is choosing. The date-heavy prose is interpretable as date-window context but adds no parameter syntax or constraints.

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 opening line names the resource and its scope precisely: historical snapshots plus changelog entries for a single carrier, which is distinguishable from the identity/lookup siblings that return current state. It lacks an explicit verb and never names a sibling for contrast, so it falls short of a 5.

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 pay-per-returned-record note and the 'exact-key miss is free' remark help an agent decide whether a call is worth making, and the empty-changelog caveat warns against misreading results. However, there is no explicit when-to-use-this-vs-lookup_carrier guidance, no prerequisites, and no explanation of when to pass since_date.

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. It usefully discloses two key traits, that the call is free and unauthenticated, but says nothing about sample size, rate limits, or the shape/content of the returned rows, so the behavioral picture is only half drawn.

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 with zero filler; the core trait (free, unauthenticated sample) is front-loaded and the rationale follows immediately.

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 tool with no output schema, the description covers cost and auth but leaves the returned content unspecified beyond 'carrier_profile rows', and does not resolve the overlap with get_identity_sample. Adequate, but missing context an agent would benefit from before calling.

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 per the rubric the baseline is 4. There is nothing about parameters for the description to clarify or omit.

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 resource ('sample of carrier_profile rows'), which is far more concrete than a tautology like 'gets a sample'. However, it does not distinguish itself from the near-twin sibling get_identity_sample, so an agent cannot tell from the description alone why both exist or how they differ.

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 clearly states the context of use: evaluate data quality before spending USDC on the paid tools. This effectively signals when to reach for this tool over the paid ones, though it never names a specific paid sibling or states a when-not condition.

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 so well: it discloses the paid pricing model ('you pay only when a call returns records; an exact-key miss is free'), warns against assuming Active by enumerating carrier_status values, and specifies that match fields return boolean/null rather than the value on file. It also flags a schema change (removed 2026-09-19).

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 and pricing are front-loaded, and every paragraph earns its place by conveying matching or return-value behavior. It is on the long side and the dated removal note adds minor bulk, but density of useful detail justifies it.

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 no-annotation, no-output-schema tool with 0% schema coverage, the description supplies pricing behavior, return-field warnings, and full claimed_* semantics. It stops short of describing pagination or the full profile's field list, but the identity-verification path an agent needs is complete.

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 0%, so the description must compensate, and it explains the five claimed_* parameters' matching semantics (claimed_name against legal_name OR dba_name; address fields against physical_address; any subset allowed) plus the name_match/physical_address_match return convention. Only usdot_number is left implicit, which is self-evident.

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 ('look up a single carrier's current profile by USDOT number') and pins the scope to one carrier, which distinguishes it from the sibling search_carriers. The agent can tell what it returns and on what key without opening the 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?

Gives a clear condition under which the claimed_* fields should be used (confirming a carrier's claimed identity, e.g. catching double brokering), which is strong contextual guidance. It does not, however, explicitly name or route away from the sibling identity tools (check_carrier_identity, screen_carrier_identity, confirm_identity_link), leaving the agent to infer boundaries.

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 so generously: it discloses that the tool never bills or requires payment, that it deliberately withholds member-identifying fields (USDOT, legal name, link type, hash), that unknown USDOT numbers produce a not_found error, and it flags the ~6% artifact rate in confidence_caveat plus the per-carrier nature of match_score_practical_ceiling.

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 purpose and the paid-triage routing are front-loaded well, but the middle paragraph is meta-rationale about the 'discovery/sales motion in an agent-only channel' and repeats that it never bills and never requires payment. That rationale is padding an agent does not need to invoke the tool, diluting an otherwise efficient definition.

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 and no annotations, yet the description qualitatively covers the return surface (flagged boolean, cluster size, linked-carrier count, confidence_caveat, practical match ceiling) and the failure mode, which is what an agent needs before calling. Only the exact response shape and field naming remain unstated, which is a minor gap for a one-parameter screen.

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 0% for the single usdot_number parameter, and the description adds only indirect semantics: that the value is a USDOT number and that an unknown one yields not_found. It conveys the error behavior but no format, validity, or source guidance for the identifier.

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 verb+resource ('free triage screen for a carrier') and enumerates exactly what it returns: FMCSA chameleon-carrier flag, identity cluster size, and count of linked carriers with a motive. It explicitly positions itself against the sibling check_carrier_identity (paid, member detail), so an agent can route without opening either 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 clearly frames itself as the free first-step triage and names the alternative ('Call check_carrier_identity (paid) for that'), giving an explicit condition that selects the paid sibling. It stops short of stating when this screen is unnecessary or inappropriate (e.g., carriers already known to be clean), so it is clear context without full 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 no annotations to lean on, the description carries the full behavioral burden and does so well: pricing behavior (paid only on non-empty results, zero-row free), default filtering to Active carriers, a hard 100-row cap, an explicit "never a full-table dump" guarantee, and a disclosure that contact fields were removed from the output. These are exactly the non-obvious traits an agent cannot infer from the empty 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?

Key operational facts (pricing, defaults, row cap, missing contact fields, alternative tool) are front-loaded and efficient. However, the aside about how a filterable multi-result endpoint returning contact details "was the sharpest version of that risk in this product" is editorial rationale that does not help an agent invoke the tool and dilutes the block.

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 and no annotations, so the description must shoulder everything; it covers output shape (no contact info) and result-size limits well. The remaining gap is filter semantics: four of six input parameters are left undefined, which is a meaningful hole for a search endpoint whose whole value is filtering.

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 0% across 6 parameters, so the description must compensate and largely does not. It explains include_inactive's default and effect and gives context for the limit cap, but state, cargo_type, safety_tier, and authority_status receive no meaning, valid values, or format guidance anywhere in the definition.

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 ("Filtered carrier search") and immediately delineates scope: multi-result, filterable, contact-information-free, capped at 100 rows. It explicitly contrasts itself with lookup_carrier for single-carrier identity confirmation, so an agent can distinguish it from that sibling without opening either 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?

Names a concrete alternative (lookup_carrier's claimed_name/claimed_street) with the condition that selects it (confirming a specific carrier's claimed identity), and gives the include_inactive condition for widening the result set. It stops short of marking when search_carriers is the wrong choice versus the screening/roster siblings, so it is clear but not fully exhaustive.

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