flatin.es — new builds and local data in Spain

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real operational context beyond that: only places with a published flatin.es page return figures, keys whose source terms disallow export answer 'not_available', and province-level fallback appears when a municipality has no data. The only missing element is an explicit error/empty-result behavior.

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 scope (2–4 places, side-by-side figures) is front-loaded in the opening clause, and the dense middle section enumerates the data domains efficiently. It is a single long sentence with some list-like padding around data sources, but nothing is redundant enough to be cut without losing coverage.

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 output schema, the description carries the return-value burden well: it states that each figure includes unit, period, level, source credit and date, plus station/POI distance, and that answers link the flatin.es pages. That is nearly everything an agent needs to interpret results; only explicit error/empty-result behavior is absent.

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 100%, so the schema already documents locale, place formats and indicator keys. The description largely restates structured constraints ('at most 12 indicators per call', province lists, buyer zone names) rather than adding new syntax or format meaning. Baseline 3 is the right call when 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 states a specific verb and resource — 'Side-by-side latest figures for 2–4 municipalities ... or buyer zones' — and enumerates the covered geography (Alicante, Málaga, Valencia, Murcia), which pins the tool's scope precisely. An agent can distinguish this multi-place comparison tool from single-figure siblings like ibi_rate or purchase_costs without opening 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?

Usage is implied by the shape of the call: use it when comparing 2–4 places across many indicators. However, no sibling tool is named and there is no explicit 'use this instead of ibi_rate when...' routing, nor any when-not-to-use guidance, so an agent must infer the boundary itself.

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 establish the safe-read profile (readOnlyHint, idempotentHint, destructiveHint=false), so the bar is lower. The description adds genuine value by disclosing the return payload fields — year, provisional flag, and source (Ministerio de Hacienda) — plus the flatin.es page reference, which matters because no output schema exists. It stops short of noting rate-limit or coverage caveats.

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?

A single compact sentence with the resource definition front-loaded and the returned fields trailing. No filler sentences, though the trailing clause is a slightly dense list.

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, the description covers what the value means, what accompanies it (year, provisional flag, source), and points to the originating page. Combined with annotations covering the safety profile and a 100%-covered schema, the definition is essentially complete; only cross-tool routing guidance is absent.

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 100%, so both parameters (municipio with its four accepted forms, and the locale enum defaulting to en) are already fully documented in the schema. The description adds nothing beyond that, which is the expected baseline here.

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+scope: the yearly IBI urbana rate for a Spanish municipality, expressed as % of cadastral value. This is unambiguous and highly specific. It does not differentiate itself from siblings like purchase_costs or non_resident_tax, so it falls short of a 5.

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?

No statement of when to use this tool versus alternatives such as purchase_costs or non_resident_tax, and no preconditions or exclusions. Usage must be inferred purely from the tool name and the property-tax definition.

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 readOnlyHint, idempotentHint and openWorldHint=false already declared, the annotations cover the safety profile. The description adds genuinely useful context beyond them: a hard cap of 'at most 25 per call,' ordering ('sorted by name'), absence of pagination, and a data-provenance caveat ('developer's own, latest check only, with attribution'). This is meaningful behavioral disclosure, though return fields are not described.

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?

It is compact and front-loads the core purpose before the operational details, with no filler sentences. The single dense sentence packs several facts (scope, cap, ordering, pagination, provenance) efficiently, though the run-on structure is slightly hard to parse.

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 output schema, the description usefully explains result size, ordering, pagination behavior, and the data source/attribution caveat, which is most of what an agent needs to call it correctly. The main remaining gap is the shape of returned fields, but the linked page reference partially covers that.

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 100%, so both parameters are fully documented in the schema itself, establishing the baseline of 3. The description mentions 'municipality, buyer zone or province' but adds no syntax, format, or disambiguation detail beyond what the 'place' schema description already provides.

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 resource and scope: 'New-build developments on sale in a municipality, buyer zone or province of the flatin.es catalogue.' An agent can immediately tell this is a listing tool for new-build property, which is clearly distinct from the tax/cost siblings. It stops short of explicitly naming or contrasting against any sibling, keeping it at a 4 rather than a 5.

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 description explains the geographic scope of inputs ('municipality, buyer zone or province') and notes the result cap and that 'the full list is on the linked flatin.es page,' which implies usage context. However, it never states when to prefer this over a sibling or any prerequisite/exclusion, so guidance is only implied.

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 establish a safe, idempotent, closed-world read, and the description adds genuinely new behavioral context: every output line cites its law and check date, rules pending validation under RDL 29/2026 are listed but not applied, and the result is an estimate rather than advice. That is disclosure beyond what the structured fields provide.

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?

Purpose is front-loaded in the opening clause and every sentence carries tax-relevant content with no filler. The first sentence is dense with parenthetical rates, which slightly slows parsing but does not waste words.

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 output schema, the description usefully signals the shape of the result (line items with law citations) and the pending-rule handling, and the parameters are fully documented in the schema. It stops short of describing the output structure or units in detail, but for a read-only calculator it is close to complete.

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 100%, so both the 1.1%/2% revised-value logic and the 19%/24% residency split are already documented per-parameter. The description restates those rates at a high level but adds no syntax, format, or edge-case detail beyond the schema, so the baseline 3 applies.

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 — computing yearly IRNR for a non-resident owner of a Spanish home — and spells out the two income branches (imputed and rental). This is clearly distinct from all siblings (ibi_rate, purchase_costs, newbuilds_in_place, compare_places), which none touch income tax.

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 domain (a non-resident owning a Spanish home) is implied by the description, but there is no explicit when-to-use framing, no prerequisites, and no reference to alternatives. The closing 'An estimate, not tax advice' is a caveat, not usage 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavior: every output line cites law, article, and verification date, and it discloses that fees use 'the general rate of the tax territory' and 'official scales' rather than any negotiated figure.

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, front-loaded with the purpose, with no filler. The legal-citation and disclaimer sentences are compact and additive, though the tax-component enumeration is somewhat dense for an opening clause.

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 output schema, the description does useful work by signaling an itemized, law-cited result. Combined with a fully documented 5-parameter schema covering the mortgage carve-out (Ley 5/2019), an agent has enough to call it correctly; only the return structure and estimation assumptions remain slightly under-specified.

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 100%, so place, locale, new_build, price_eur, and mortgage_eur are all fully documented in the schema. The description's tax-regime explanation largely restates the new_build schema text, adding little parameter-level detail beyond confirming that place drives the applicable regional rate.

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 precise resource (taxes and fees of buying a home in Spain) and enumerates the specific components computed: VAT + AJD for new builds, ITP for resales, plus notary and registry fees. This cleanly separates it from siblings like ibi_rate (annual property tax) and non_resident_tax.

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 scope implies usage (compute closing costs for a purchase) and the new_build distinction routes between the two tax regimes. However, there is no explicit guidance on when to use this versus compare_places or newbuilds_in_place, and no stated prerequisites or exclusions beyond the 'estimate, not tax advice' caveat.

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