IleM² – ceny nieruchomości w Polsce

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

Annotations already declare this as a safe, read-only, idempotent operation. The description adds important behavioral context beyond annotations: only cells meeting the 6/6 threshold are published, lower counts appear as 'mniej niż 6', and urban plot data uses a 3–5 sale interval. This thresholding and suppression behavior is exactly the kind of disclosure annotations cannot 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?

The description is dense and front-loads the tool's scope and return content before the threshold caveat. The bilingual duplication effectively doubles the length, but it contains no filler and every sentence carries substantive information.

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 identify the returned statistics and threshold suppression, which is useful. However, it does not clarify response shape—such as whether multiple cells are returned, ordering, or behavior when the area cannot be resolved—leaving some gaps for an agent building a complete call expectation.

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 all four parameters thoroughly, including accepted formats for miejsce and choices for rodzaj, okres, and podzial. The description adds a threshold constraint relevant to interpreting okres results, but otherwise largely restates what the schema 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 clearly identifies the resource: price cells from the IleM² publication for municipalities, cities, districts, cadastral areas, or point hexagons, including the statistics returned (counts, median, quartiles). It is specific but does not explicitly distinguish itself from siblings such as szacunek_mieszkania or raport.

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 area-level scope implicitly signals that this tool is for looking up aggregate price statistics rather than valuing a single property, but there is no explicit when-to-use guidance or routing to sibling tools. An agent must infer the appropriate context from the granularity described.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful content-level context — that the response includes asking-price summaries, a market sentence, development stage and links — which matters since there is no output schema, but it says nothing about ordering, fallback when an area is unknown, or result completeness.

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 two compact sentences with the core resource front-loaded in the Polish sentence and a condensed English restatement. The bilingual duplication costs some space but is a deliberate pattern; every clause (cenniki, zdanie o rynku, ceny ofertowe, etap, linki) carries information.

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 sketches what comes back: asking-price summaries, a market comment, and a list with prices, stage and links. Combined with annotations covering the read-only, closed-world profile and a fully documented schema, an agent has enough to invoke it correctly; only edge-case behavior (unknown area, empty result) is unaddressed.

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 limit (1–20, default 10), obszar (name/slug/TERYT) and pokoje. The description adds a small amount by broadening obszar to include gmina, miasto, powiat, województwo and dzielnica, which the schema only hints at, but it says nothing about limit or the pokoje filter.

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 a specific verb+resource: it returns developer developments in a given area, including price summaries, a market comment, and a list of investments with asking prices, stage and links. The scope is concrete and the enumerated area types (gmina, miasto, powiat, województwo, dzielnica) make it distinguishable from ceny_obszaru or the szacunek_* valuation tools, but 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?

Usage is only implied: the agent can infer this is the tool for browsing new developments in a location, but the description never states when to prefer it over ceny_obszaru (area price statistics) or znajdz_nieruchomosc (searching individual listings). No exclusions or prerequisites are given.

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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds one genuinely useful behavioral caveat — prices come only from statistics with a threshold and exclude individual transactions — plus the note that szczegoly=true yields a larger response, but it says nothing about cost, latency, or rate limits for a potentially heavy report generation.

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 purpose and deliverable are front-loaded in a single dense sentence, with the English rendering serving as a condensed summary rather than a verbatim duplicate. The one wasted-adjacent element is that the pricing caveat appears only in the Polish half, making the two halves asymmetric.

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 the work of describing the return: answers, sections with signals and sources, and links to page, PDF and JSON, plus how szczegoly enlarges the payload. Annotations already carry the safety semantics, so nothing essential for calling it correctly appears to be missing.

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 cel formats, sekcje and szczegoly, giving a baseline of 3. The description corroborates the parameter meaning by naming the three cel variants (parcel, building, point) and the section/signal concept, but adds no syntax or format detail beyond the schema.

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 gives a specific verb-and-resource: it produces an IleM² report for a parcel, a residential building, or a point, organized as answers to five named questions with sections, signals, sources and links to page/PDF/JSON. This clearly separates it from single-value siblings like szacunek_dzialki or ceny_obszaru, though it never names those siblings 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?

Usage is implied by the breadth of the deliverable (five questions, multiple output formats), so an agent can infer this is the 'full report' option. However, there is no explicit when-to-use/when-not guidance and no reference to the valuation or search siblings that are the obvious alternatives.

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 read-only, idempotent, non-destructive and closed-world, so safety is not the description's burden. The description goes further by disclosing analytical limitations (no scoring, no revenue forecasts), the gallery-specific variant behavior, the anonymization rule (exact counts, chain names only), and that both a web page and PDF link are returned.

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?

All content is relevant, but it arrives as one dense bilingual block with the English summary trailing the long Polish paragraph, so the key purpose is not front-loaded for a non-Polish-reading agent. Many output-detail clauses (parking at 50/100 m, GUS bed counts, university proximity) could be trimmed or moved without losing call guidance.

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 burden of explaining returns, and it does so thoroughly — competitor counts, reach radii, zoning/legal checks, `opis_miejsca` contents, gallery comparison, and page/PDF links. It is nearly complete for a 2-parameter read tool; only response format details (language of output, latency) are unstated.

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 `typ` (industry list) and `miejsce` (address/plot/coordinates/report URL) are already fully documented, making 3 the baseline. The description adds industry examples but also mentions a `galeria` field that is not an input parameter, which risks confusing input/output boundaries without adding real parameter guidance.

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 a specific deliverable (business location report for a place + line of business) and enumerates its contents: 500 m competitor counts, residents in reach, transit, zoning, closure rates. That is enough to distinguish it from generic estimate tools, but it never names or contrasts with siblings like `raport` or `ceny_obszaru`, so an agent must infer the boundary.

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 context is implied by the industry-focused framing and by the explicit scope limit ('facts without forecasts', 'does not evaluate the place or predict turnover'), which tells an agent what questions this tool cannot answer. However there is no explicit when-to-use/when-not rule and no routing to an alternative sibling, so the agent still has to guess which report tool to pick.

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?

Beyond the safe read-only annotations, the description explains the returned estimate structure: middle half, 80% interval, confidence, justification sentence, and aggregated comparisons. It also discloses that a single number appears only at high confidence, area is estimated from building outline/floor count unless supplied, and the result is not a formal valuation.

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 purpose is front-loaded, but the description is a dense, run-on Polish sentence with nested parentheses. Most content is relevant, yet the structure makes it harder to scan than necessary for an agent selecting and invoking the tool.

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 a good job explaining the estimate's statistical output, confidence behavior, area estimation, and fallback to cena_obszaru. It is nearly complete, though the mention of 'pokaz_liczbe' is confusing because no such parameter appears in the input schema.

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 lat/lon, pow_m2, and budynek. The description mostly mirrors those meanings (area estimated from outline/floors unless provided; budynek or lat/lon) and adds the cena_obszaru fallback, but it does not add substantial parameter syntax or semantics beyond the schema.

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 a specific resource (single-family house) and a specific operation (statistical price estimate). It clearly distinguishes this from sibling apartment/land estimation tools through the repeated 'domu jednorodzinnego' scope and mentions the building-card/report context.

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 house-specific scope, and it notes a fallback to typical area prices when no local model exists. However, it does not explicitly say when to choose this over siblings such as szacunek_mieszkania, szacunek_dzialki, ceny_obszaru, or raport.

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 that this is a read-only, idempotent, non-destructive operation. The description adds meaningful behavioral context: it returns an 80/100 interval, a confidence level, comparisons, and a single number only at high confidence, and it clarifies the statistical rather than formal-valuation nature. It does not cover edge cases such as missing or conflicting location inputs.

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 purpose is front-loaded in the opening phrase, and the remaining details about output and caveats are relevant. The Polish sentence is dense and run-on, but most clauses earn their place by describing return components and usage constraints. The English summary adds accessibility without much duplication.

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?

There is no output schema, so the description must carry the return-value burden, and it does so by naming the main estimate components, interval, confidence, justification, comparisons, and area reference. Combined with full parameter schema coverage and read-only annotations, this is close to complete. Minor gaps remain around behavior with no inputs or when both identifier and coordinates are provided.

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 all four parameters. The description adds useful routing detail by saying to provide either a plot identifier or coordinates, and that coordinates produce a typical local plot. It does not explain the optional pole parameter or precedence when both identifier and coordinates are supplied.

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 clearly states a specific verb and resource: a statistical price estimate for a vacant residential plot. It also adds the important caveat that this is not a formal valuation. Sibling differentiation is mostly implicit through the property type, rather than by explicitly naming alternatives like szacunek_domu or ceny_obszaru.

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 tells the agent how to provide input, either an EGiB plot identifier or coordinates, and notes that coordinates imply a typical local plot. It also excludes formal valuation use. However, it does not explicitly say when to use this tool versus sibling tools such as ceny_obszaru or raport.

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 cover read-only/idempotent safety, so the bar is lower; the description nonetheless adds meaningful behavior: output is an 80% interval, a single number appears only at high confidence, and the value matches the building card, map and report. The 'not a formal valuation' caveat adds important expectation-setting.

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 purpose and the input rule are front-loaded, but the description is a dense, slash-separated bilingual run-on that mixes output shape, input rules and disclaimers into one block, making it slower to parse than necessary.

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 correctly compensates by describing the return values (interval, unit, confidence, justification sentence). For an 8-parameter, all-optional estimation tool the coverage is nearly sufficient; only the sibling-choice guidance is thin.

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 100%, so baseline is 3, but the description adds real meaning beyond it: the either/or relationship between budynek, adres and lat/lon, and the behavioral consequence of omitting metraz. This helps the agent choose inputs rather than just format them.

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: a statistical price estimate for an apartment, with the output shape (80% interval, PLN/m², confidence, justification). It implicitly separates itself from szacunek_domu/szacunek_dzialki by naming the resource, but never explicitly contrasts with those siblings.

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?

Tells the agent what to supply (building number from the report, address, or coordinates plus floor area) and clarifies the fallback when only a building is given (typical second-hand flat). It also flags the 'not a formal valuation' limitation and the pokaz_liczbe condition, though it does not name when to prefer a sibling tool.

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 and closed-world, so safety is covered. The description adds real value by disclosing what comes back — candidate type, label, the `cel` parameter and page/PDF links — which is essential since no output schema exists. It does not say what happens with zero or many matches.

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 information is front-loaded and useful, but the definition is bilingual and the English sentence largely repeats the Polish one while dropping detail, so a portion of the text is redundant rather than additive.

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?

Given one input, no output schema and strong annotations, the description covers input formats and return contents well enough to call the tool correctly. The remaining gap is the outcome when a query is ambiguous or matches nothing, which matters for a candidate-resolution tool.

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?

With a single fully documented parameter the baseline is 3, but the description goes beyond the schema by spelling out the EGiB id example format (120617_2.0018.927/87) and the 'szerokość, długość' coordinate convention, which the schema only alludes to.

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 a concrete transformation: address / EGiB parcel id / coordinates into report candidates, and enumerates the returned fields (rodzaj, etykieta, cel, links). That is far more than a restatement of the name. It stops short of a 5 because it never names a sibling explicitly (e.g. `raport` as the consumer) even though 'kandydatów do raportu' hints at the pipeline.

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 rather than stated: the agent can infer this is the lookup step that feeds `raport`, and the accepted input shapes are listed. There is no explicit when-to-use / when-not-to-use guidance and no named alternative among siblings such as `raport` or the `szacunek_*` tools.

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