Tankful: Irish heating oil prices

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds genuinely non-structured context: the guide may be unavailable, and results carry an observation date and confidence level. It stops short of saying what an unavailable state looks like.

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 compact sentences with no filler: capability first, reliability caveat second, scope exclusion last. Every sentence carries distinct information an agent needs.

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, three-parameter tool with a full output schema and rich annotations, the description covers availability risk and result provenance (date, confidence) rather than restating returns. Lacking only an explicit pointer to the sibling tool for actual quotes or ordering.

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 only 33%, but the description compensates by naming the three litre bands and the kerosene-only fuel type, matching the enum and const. The county dimension is only implied by 'county reference guide'; the schema's own note about not passing addresses/Eircodes does the remaining work.

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 (read) and resource (published kerosene county reference guide) plus the exact litre bands it serves. The closing line 'Not a supplier quote or bookable offer' separates it from tankful_find_suppliers and tankful_delivery_request_draft without needing their schemas.

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?

'May be unavailable' and 'Not a supplier quote or bookable offer' give a clear use context and one explicit exclusion, so an agent knows this is reference data only. It never names a sibling as the alternative for the excluded cases, so routing still requires 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 already declare readOnlyHint=true and destructiveHint=false, and the description reinforces this with an explicit negative list: does not send, persist, order, reserve, take payment, or collect personal details. That is genuinely useful disambiguation for an agent worried about side effects, though it does not explain the handoff mechanism.

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 sentences, both load-bearing: the first states inputs and the continuation, the second enumerates non-effects. Slightly compressed phrasing but zero filler and front-loaded constraints.

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?

An output schema exists, so return values need not be described, and the safety profile is covered by both annotations and the explicit negative list. The remaining gap is routing against the two sibling tools, which the description does not address.

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 only 25% (county alone is documented), so the description must compensate, and it does: it names fuel, the 300–5000 range with 'whole litres' (clarifying integer semantics), and timing preferences (urgency). Enum values themselves are left to the schema, which is acceptable.

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 inputs it prepares (county, fuel, litres, timing) and states the outcome is a handoff to 'continue on Tankful', which fits the 'draft' name. It never says what the tool actually returns (a review step, a deep link), so the agent knows the domain but not the artifact.

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 phrase 'then continue on Tankful' implies this is a first step in a flow, but neither sibling (tankful_county_price_guide, tankful_find_suppliers) is named, and there is no statement of when to pick this versus them. Usage is inferable but not 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 already declare readOnly/idempotent/non-destructive, but the description adds real value beyond them: the five-result ceiling and the caveat that results blend 'confirmed coverage' with 'directory coverage' (i.e., some entries are unverified). It also sets expectations for what is deliberately absent (live stock, prices, delivery promises, contact details), which prevents misreading of results.

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 primary capability and result cap come first, followed by the data-quality caveat and the negative scope. No filler, no restatement of the title.

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?

An output schema exists, so return shape need not be described, and the description covers scope, result limit, and data-vs-directory reliability. Only minor gaps remain (default fuel behavior, and whether results are empty for uncovered counties), which the enum-only schema doesn't resolve.

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 50% — county carries its own description and both params are enums, so the schema does most of the work. The description confirms the two dimensions (county and fuel) but adds no semantics for the fuel enum (KEROSENE/GAS_OIL/HVO) or its KEROSENE default, so a 3 baseline is 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 and resource ('List ... public oil suppliers'), the result cap ('up to five'), and the exact scoping dimensions (Republic of Ireland county + fuel). The closing clause ('No live stock, prices, delivery promises or contact') implicitly separates it from the price-guide sibling, so an agent can tell what this tool is and is not without reading 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?

Clear context for use: a county plus a fuel type, with the note that a county only (no address/Eircode) is expected. The 'no prices / no contact' clause steers price or quote requests toward tankful_county_price_guide, but the alternative is never named explicitly, so the routing is inferential rather than stated.

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