ValveRide Flow

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

Annotations already declare readOnly, idempotent, and non-destructive hints. The description adds valuable behavioral context: the data is cached and refreshed every 12 hours, it returns specific percentiles, and it selects states based on origin/destination. It also mentions 'typical optimized-savings context' as an extra output. No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded: the first sentence states what the tool is and its refresh cadence, the second describes output, the third gives usage guidance and alternative, and the fourth mentions cost. Each sentence earns its place with no fluff.

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 snapshot tool with two optional parameters and no output schema, the description is complete. It explains the returned data (national and per-state percentiles), how states are chosen, the caching behavior, and the no-charge aspect. An agent has enough to decide when to call and what to expect.

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 schema already provides 100% coverage of both parameters, describing them as optional place strings used to pick states. The description reinforces this ('for any states mentioned in origin/destination') but adds no new semantic information beyond the schema. Baseline 3 is appropriate since the schema does the heavy lifting.

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's function: a cached US diesel market snapshot providing national and per-state percentiles. It uses a specific verb ('returns') and resource, and distinguishes itself from the sibling optimize_fuel_plan by naming what it does not do (stop-by-stop planning). This leaves no ambiguity about the tool's purpose.

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 to use this tool ('market questions or cost estimates') and when to use the alternative ('optimize_fuel_plan when you need an actual stop-by-stop plan'). It also notes the tool carries no charge, which is relevant for cost-sensitive decisions. This is clear routing guidance.

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?

Even with annotations present, the description reveals behavior annotations cannot: the no-fallback vendor rule and its structured error no_feasible_plan_under_vendor_rule, the $2.25 vs $0.08 billing split, and the fact that the response echoes vendorRule and appliedDiscounts. No contradiction exists with the readOnlyHint or idempotentHint flags.

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 text is densely packed and front-loaded with the core purpose, and the VENDOR RULE block is clearly flagged. It is longer than strictly necessary and repeats some schema-level vendorRule detail, but each section adds operational value.

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?

Despite 10 parameters and no output schema, the description covers end-to-end behavior, key outputs, replan semantics, pricing rates, and the vendor-rule failure mode. Optional knobs remain documented in the schema, so nothing critical for correct invocation 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?

Although schema coverage is high, the description adds crucial inter-parameter meaning: how vendorRule.allowedVendors and discountSchedule must be paired in the same call, with a concrete '10 cents off at Love's' example, and how tripId plus currentLocation/currentFuelGallons drive replanning. This goes beyond the schema's isolated parameter descriptions.

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: 'Build an optimized diesel fuel plan for a truck route,' then enumerates the pipeline and concrete outputs including stops, gallons, savings, and a tripId. This is clearly distinct from the sibling fuel_market_snapshot, which is about market pricing rather than constructing a route plan.

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 gives clear operational context: when to create a new trip versus replan mid-trip with a tripId and currentLocation, and when the vendorRule must be set. It does not explicitly contrast with fuel_market_snapshot or state a when-not-to-use, so it stops short of a 5.

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