LandBNG

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

With no annotations, the description carries the full burden and does real work: it discloses cost (free), authentication (no key), geographic coverage limits, and the nature of the response (headroom, RAG status, siting signal). Not disclosed: behaviour for coordinates outside GB, coordinate reference system, or data freshness — the kind of edge-case guidance a location-based lookup would benefit from.

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, each carrying distinct payload: capability + returned metrics first, then geographic scope, then cost/auth. Nothing is repeated from the schema and no sentence is filler — 'Free, no key' and the non-England coverage note both earn their 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?

An output schema exists, so the description need not explain return values, and it wisely only summarizes them. For a two-parameter read-only lookup this is nearly sufficient; the sole substantive gap is the coordinate format/CRS, which leaves the calling agent exposed on input construction.

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 0% — neither lat nor lon has any documentation in the schema — so the description must compensate, and it does not. It only says 'for a location' without specifying decimal degrees vs. other notation, WGS84/EPSG:4326, acceptable ranges, or precision. An agent must guess the coordinate convention for a tool that fails silently on wrong input.

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 (check), a specific resource (nearest DNO grid connection headroom) and enumerates the payload: generation/demand headroom in MW/MVA, RAG status, voltage, and a combined BNG+grid siting signal. The domain (electricity grid capacity) is unmistakably distinct from the sibling tools covering planning history and BNG cost/income, so an agent can route without opening any 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?

'Covers all of Great Britain (England/Scotland/Wales), not just England' gives an explicit scope boundary that tells the agent when this tool applies geographically, and 'Free, no key' removes a common pre-call blocker. It stops short of naming a sibling or stating a when-not-to-use condition, but the domain separation from the BNG and planning siblings is self-evident.

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?

Since no annotations are provided, the description carries the full behavioral burden. It successfully adds crucial operational context regarding the tool's access method (UK PlanIt's public aggregator) and cost (free/no key).

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 definition is highly dense and efficient, packing scope (UK planning), method (public aggregator), access constraints (free/no key), and input constraints (radius range) into a single, coherent sentence.

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?

The tool provides strong high-level context regarding geographic scope and operational requirements. However, because it only defines one parameter's constraint, the complete definition relies heavily on external knowledge of coordinate systems (lat/lon).

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 0%, so the description must compensate fully. While it defines the acceptable range for radius_km, it fails to describe the meaning or expected format of the critical lat and lon parameters, which are simply required for a 'UK location'.

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 tool clearly defines its purpose as finding planning applications near a UK location. It distinguishes itself sharply from the siblings by focusing on planning history rather than grid connection or cost estimation.

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 provides specific operational constraints, noting the function is free and requires no key. It also defines the mandatory range for the radius parameter (0.1 to 5.0).

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 does well: it discloses the pricing basis (two Defra credits per unit), the spatial risk multipliers 1.0/0.75/0.5, the England-only scope, and 'Free, no key.' It omits output units/currency, but an output schema exists.

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?

Front-loaded with the purpose and free of filler, but the single run-on sentence crams multipliers and enums into nested parentheticals, making the exact cost formula hard to parse on first read.

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 4-parameter computational tool with an output schema and no annotations, the description supplies region, pricing logic, land types, and multiplier semantics. Missing only output units/currency and any assumption about minimum scheme size.

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 0%, so the description must compensate, and it largely does: it defines scheme_ha as hectares, enumerates land_type values (brownfield/arable/improved/semi_improved/mixed), and explains that lat/lon resolve the point's authority for the spatial multiplier. It doesn't state formats or bounds for lat/lon or scheme_ha.

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+resource: estimating the cost of meeting England's 10% BNG requirement for a scheme of `scheme_ha` hectares. The word 'cost' naturally separates it from the sibling estimate_bng_income, though no sibling is named explicitly.

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?

Implies usage context via 'England only' and the land_type vocabulary, and the cost-vs-income framing hints at the alternative tool. However, it never states when to pick this over estimate_bng_income or what prerequisites/inputs are 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 burden and does well: it discloses the valuation model (LandBNG planning assumptions per habitat), the price cap (Defra statutory credit price), and that local factors such as flood zone, SSSI and Green Belt are listed but explicitly not priced. It does not cover failure behavior for out-of-England coordinates, which keeps it short of a 5.

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 core action, horizon, output scenarios, and input are front-loaded in the first clause, followed by methodology and then hard constraints ('England only. Free, no key.'). No sentence is filler despite the density.

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-value shape need not be described. The description supplies the assumptions, the price cap, the geography restriction, and the explicit scope limit on local factors. The main remaining gap is what the tool does with out-of-scope coordinates or invalid area values.

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 0%, so the description must compensate. It clarifies 'area_ha' as hectares of an England parcel and implies lat/lon locate that parcel, but it adds no format, range, precision, or coordinate-system detail beyond that; coordinate semantics and validity bounds remain undocumented in both schema and description.

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 verb and resource are specific: 'Estimate 30-year lump-sum BNG income' with LOW/MID/HIGH scenarios for a given hectare area. The income framing plus the explicit methodology (LandBNG assumptions capped at the Defra statutory credit price) makes it distinguishable from the sibling estimate_bng_cost without opening either 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?

'England only' is a real usage constraint, and 'Free, no key' tells the agent there is no auth prerequisite. However, it never routes the agent explicitly to or away from estimate_bng_cost, nor states what happens if the parcel is outside England; the when-to-use signal is implied by the word 'income' rather than stated.

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