UK Fuel Price Finder MCP

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

No annotations are provided, so the description carries the full behavioral burden. The leading "PRO." hints at a paid/subscriber tier and the schema documents the access_token, but the description says nothing about rate limits, error behavior when a postcode is unknown, or whether results are cached/live. It does at least disclose the shape of the aggregate returned (min/avg/max plus cheapest brand).

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?

One tight sentence with the core capability front-loaded ahead of the use-case clause. The cryptic "PRO." prefix costs a little clarity but adds no bloat.

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, no output schema and only a third of parameters documented, the description should do more: auth requirements, defaults for the optional radius, and what happens on invalid postcodes are all unaddressed. Adequate to identify the tool, thin for calling it confidently.

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 33% — only access_token is documented. The description partially compensates by clarifying that the radius is measured around the postcode and that results are grouped per fuel type, but it omits postcode format/region, radius units and default value.

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 pair: min/average/max price per fuel type within a radius of a postcode, plus cheapest brand. An agent can tell this is an aggregate/benchmark query rather than a single-station lookup, but it never names the sibling tools (cheapest_fuel, fuel_search) to sharpen that distinction.

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?

"For pricing, expenses and mileage rates" implies a usage context but gives no explicit when-to-use versus fuel_search or cheapest_fuel, and no exclusions. The agent must infer that this is the tool for area-level statistics rather than point lookups.

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 it does disclose useful traits: the call is free, the search radius is fixed at 5 miles, exactly 3 results are returned, and prices are in pence per litre. It omits auth/prerequisite needs, the behavior when fewer than 3 stations exist, and whether the radius is configurable.

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 fragments with the strongest hook ('FREE') front-loaded and zero filler. Slightly telegraphic phrasing, but every element 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?

For a simple two-parameter lookup with no output schema and no annotations, the description covers the essentials (result count, radius, unit). It stops short of covering the omitted-fuel default and the empty-result case, which an agent would need to call it confidently.

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%: 'fuel' is documented in the schema with its four grade codes, but 'postcode' has no description. The description adds the price unit and confirms postcode scoping, but does not explain the optional 'fuel' parameter's default when omitted, which is the main semantic gap.

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 resource (cheapest 3 UK fuel stations), a concrete scope (within 5 miles of a postcode) and the unit (pence per litre). It is clear what the tool returns, though it never contrasts itself with the sibling fuel_search or area_benchmark.

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?

There is no when-to-use or when-not-to-use guidance and no mention of fuel_search, which by name appears to overlap heavily. The only routing hint is the word 'FREE', which implies a cost tradeoff but never names the alternative.

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 supplied, so the description carries the full burden. It does add real context beyond the schema — the 20-postcode cap (absent from the array schema, which has no maxItems) and the returned metrics — but omits auth/token requirements, rate limits, error behavior, and what happens when the cap is exceeded.

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?

One tight sentence with the report purpose front-loaded and the output metrics named up front. The leading 'PRO.' fragment is unexplained noise, but the rest wastes nothing.

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 5-parameter, no-annotation, no-output-schema tool, the description adequately covers what comes back (cheapest station, saving per fill) but leaves the input side thin — no defaults for radius_miles or tank_litres, no auth guidance, and no handling for oversized postcode lists.

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 40%: fuel and access_token are described in-schema, while postcodes, tank_litres, and radius_miles are not. The description partially compensates by clarifying postcodes as depot/site locations with a 20-item limit and implying tank size via 'saving per fill', but radius_miles and tank_litres remain unexplained.

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 — a batch "Fleet report" over depot/site postcodes that returns the cheapest nearby station and the saving per fill vs local average. The batch/multi-site scope implicitly separates it from the single-location siblings (cheapest_fuel, fuel_search, area_benchmark), though none are named.

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 only implied: 'up to 20 depot/site postcodes' signals this is the multi-site batch variant, but the description never says when to pick it over area_benchmark or cheapest_fuel, nor what to do above 20 postcodes or whether a subscription is required.

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 behavioral burden. It usefully discloses ordering (cheapest first), radius cap (up to 30 miles), and that results include all fuel prices and savings versus local average. However, it omits auth requirements, rate limits, and explicit read-only confirmation despite the access_token parameter.

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 a single efficient sentence with no wasted words. 'PRO.' is terse but potentially useful as a tier marker, though it slightly delays the core purpose.

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 5-parameter search tool with no output schema and no annotations, the description is partially complete: it explains return content and ordering, and the radius cap. It does not explain the limit parameter, auth flow, or how this differs from sibling tools, so an agent still lacks key context.

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 40%, so the description must compensate. It clarifies postcode, radius_miles cap, and fuel scope, while the schema already describes fuel and access_token. The limit parameter remains undocumented in both schema and description, leaving a meaningful gap.

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 action and resource: find all fuel stations within a radius of a postcode, sorted cheapest first, with prices and savings. It is clear what the tool does, but it does not explicitly distinguish itself from siblings like cheapest_fuel or area_benchmark.

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?

There is no guidance on when to use this tool versus alternatives, no exclusions, and no prerequisites beyond the implied postcode search. The sibling tools cheapest_fuel and area_benchmark are not mentioned, leaving the agent to infer the appropriate choice.

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