NexusFeed: LTL Freight Intelligence

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

With no annotations provided, the description carries full disclosure burden. It excels at transparency by explicitly stating the tool is non-functional ('will return an unavailability message'), which is critical behavioral information. It does not mention auth requirements or rate limits, but the unavailability status is the dominant behavioral trait for this placeholder tool.

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 efficiently structured: status/purpose first, behavioral reality second, alternative recommendation third. Every sentence earns its place with no redundant fluff. The '[COMING SOON]' tag front-loads the critical status 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?

Given the tool has an output schema (reducing need to describe return values) and is a simple 2-parameter tool, the description adequately covers the essential context: purpose, unavailability status, and alternative routing. The only gap is parameter semantics, which are partially implied by example lists but not explicitly documented.

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 has 0% description coverage (only titles). While the description lists example fee types (liftgate, residential, etc.) that align with the 'fee_types' parameter, it fails to explicitly document what either parameter does (e.g., 'carriers' filters by carrier IDs, 'fee_types' filters by specific accessorial types). With zero schema coverage, the description must compensate more explicitly.

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 clearly states the tool returns 'accessorial fee schedules for LTL carriers' and lists specific examples (liftgate, residential delivery, etc.). It distinguishes itself from sibling ltl_get_fuel_surcharge by directing users to that tool instead. However, the '[COMING SOON]' prefix and unavailability warning slightly complicate the purpose statement by contrasting intended vs. current behavior.

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 states when NOT to use the tool ('not yet available and will return an unavailability message') and names the specific alternative ('Use ltl_get_fuel_surcharge for current carrier data'). This provides clear guidance on tool selection given the current implementation state.

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 provided, so description carries full burden. Discloses critical behavioral traits: weekly extraction schedule, caching with <500ms response time, data source (carrier tariff pages), and response structure (_verifiability block with timestamp/confidence score). Excellent transparency for audit-critical data.

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 dense sentences with zero waste: purpose (sentence 1), performance/alternative (sentence 2), coverage (sentence 3), response structure/caution (sentence 4). Minor deduction for structure: the 'Use this instead' guidance could be front-loaded earlier for immediate context.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists, description appropriately focuses on data provenance and trustworthiness rather than return value structure. Covers extraction methodology, freshness, confidence scoring, and audit reliability. Only gap is parameter documentation, which is significant given 0% schema coverage.

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 has 0% description coverage, requiring description to compensate. While 'DOE diesel price' hints at include_doe_price and carrier names (ODFL, SAIA) suggest valid values for carriers, the description fails to explain the weeks parameter (historical range?), carriers parameter structure (array of codes?), or that include_doe_price is a toggle. Insufficient for 0% schema coverage.

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?

Description explicitly states it 'Returns current LTL carrier fuel surcharge percentages and the DOE diesel price' — specific verb + resource combination that clearly distinguishes it from sibling ltl_get_accessorials (accessorial fees vs. fuel) and ltl_list_carriers (listing vs. retrieving rates).

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?

Provides explicit guidance: 'Use this instead of browsing carrier websites' with clear rationale ('JS-rendered, PDFs, or require session state'). Also specifies appropriate use cases ('freight cost calculation or invoice audit') and coverage limitations (ODFL/SAIA now, others in Sprint 4).

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 are provided, so the description carries the full burden. It discloses the specific data fields returned, which helps set expectations, but fails to mention operational characteristics such as whether this is idempotent, cached, rate-limited, or error-prone. For a read operation with no safety annotations, this is adequate but has clear gaps regarding operational 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 well-structured sentences with zero waste. The first sentence front-loads the core functionality with specific return value details, while the second provides workflow context. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (reducing the need for detailed return value description) and zero parameters (low complexity), the description provides appropriate workflow context. It effectively explains the discovery pattern ('discover coverage before building') which is essential for agent tool selection.

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 input schema contains zero parameters. Per calibration guidelines, zero-parameter tools receive a baseline score of 4. The description does not need to compensate for missing parameter documentation.

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 specific verb ('Returns') with clear resource ('metadata for all LTL carriers') and enumerates specific fields returned (SCAC code, data products, fuel surcharge update day, extraction method). It clearly distinguishes from siblings 'ltl_get_accessorials' and 'ltl_get_fuel_surcharge' by focusing on carrier discovery/metadata rather than specific pricing data retrieval.

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?

Provides explicit when-to-use guidance ('Use this to discover coverage before building a carrier comparison workflow'), establishing it as a prerequisite discovery step. However, it lacks explicit when-not-to-use guidance or direct mention of sibling tools as alternatives for subsequent steps.

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