OilPriceAPI

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

With no annotations provided, description carries full disclosure burden. It adds value by stating data freshness ('latest') and output format ('Returns a table'), which helps agent predict response shape. However, lacks other behavioral traits: no mention of default behavior when unfiltered, update frequency, rate limits, or whether data is real-time vs delayed.

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 well-structured sentences with zero waste: [Purpose] -> [Usage Trigger] -> [Parameters] -> [Return Value]. Front-loaded with specific action, domain terminology placed where needed for sibling differentiation, and output format specified at the end. Appropriate length for tool complexity.

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 2-parameter retrieval tool without output schema or annotations, description adequately covers the essential gaps: purpose, usage triggers, parameter examples, and return type. Missing only minor details like explicit confirmation that both filters are optional (though implied by 'Can filter') or explaining fuel type acronyms.

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 100% description coverage with examples (SINGAPORE, VLSFO, etc.), establishing baseline of 3. Description repeats these same examples without adding supplementary semantic context (e.g., explaining VLSFO=Very Low Sulfur Fuel Oil, or noting that port names must be uppercase). Does minimally reinforce optionality via 'Can filter by' phrasing.

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?

Excellent specificity: verb 'Get' + resource 'marine fuel (bunker) prices' + scope 'major shipping ports'. Explicitly distinguishes from siblings like opa_get_price (generic) and opa_get_diesel_by_state (automotive vs marine) by specifying 'marine fuel', 'bunker', and shipping-specific fuel codes (VLSFO, MGO, IFO380).

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 'Use when...' sentence listing specific trigger terms (bunker fuel, VLSFO, MGO, IFO380, shipping fuel costs) provides clear positive guidance. While it lacks explicit 'when not to use' or named alternatives, the domain-specific terminology effectively differentiates from sibling tools like opa_get_futures or opa_get_diesel_by_state.

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