Realistimo

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful scope context (amounts in euros; conditional outputs such as rent/yield with an apartment plus area, and loan plus monthly payment with a mortgage), but discloses nothing about auth, rate limits, or precision/rounding behavior beyond the schema.

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-loads the resource definition in the first sentence before listing components, and the second sentence covers conditional outputs. It is somewhat run-on and the long chain of Bulgarian example queries makes it longer than needed, but no sentence is purely filler.

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 an output schema present and 100% parameter coverage, the description need not explain return values, and it adequately frames the computation's inputs and conditions (mortgage, apartment with area, seller tax basis). The main omission is explicit discrimination from realistimo_estimate_price when a user asks about property figures.

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 every one of the 15 parameters is already documented, and the description largely restates the same content (e.g. mortgage adds bank fees, area enables rent/yield, location affects the local tax). It adds only the global note that amounts are in euros, which is the baseline-3 case where 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?

States a precise resource and scope: extra transaction costs of buying/selling property in Bulgaria, and enumerates the concrete components (notary fee, registration, local acquisition tax, broker commission, seller's income tax, mortgage fees). This is clearly distinct from siblings like realistimo_estimate_price and realistimo_market_stats, which address price and market data rather than transaction costs.

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?

Provides concrete trigger utterances in Bulgarian („колко струва покупката/продажбата", „нотариални такси", „колко пари ми трябват за апартамент за 120 000 евро") that make the intended usage unambiguous. It does not, however, state when NOT to use it or explicitly route the agent to a sibling such as realistimo_estimate_price.

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/closed-world profile, and the description adds real context beyond them: the estimate is a median of live asking prices, the askingPrice input triggers percentile positioning (below cheapest 10%, around median, above dearest 10%), and it is explicitly not a valuation. This tells the agent how much to trust the number, though nothing is said about data freshness or coverage limits.

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 core explanation, followed by the optional askingPrice behaviour and the use-case phrases — a logical order with no filler sentences. The opening sentence is long and densely packed, which costs some readability, 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?

With an output schema present the description need not explain return values, so what remains is covered: calculation method, geographic scope, the askingPrice extension, and the not-an-appraisal caveat. An agent has everything required to call this correctly and interpret the result.

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 the baseline is 3, but the description goes further by explaining what location scoping means (oblast capital or its квартали), that area is multiplied against the per-m² figure, and what askingPrice actually does behaviourally. That is meaningful interpretation layered on top of the schema rather than repetition.

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?

Names a specific operation and resource — a sale/rent asking-price estimate for a Bulgarian property — and spells out the method (median asking price per m² of live listings × area). It is clear what the tool produces, but it never distinguishes itself from the sibling realistimo_market_stats, which is implied by the phrase 'the figures of its price statistics pages' yet not 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?

Gives concrete trigger phrases in Bulgarian ('колко струва апартаментът ми', 'колко наем да искам', 'скъпа ли е тази обява') and an explicit exclusion, 'Not an appraisal.' It does not, however, route the agent toward or away from the sibling tools (market_stats, market_index, deal_cost), so the boundary with alternatives is left implicit.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds the default-edition behavior and the content scope, but describes the return contents that the output schema already documents, and says nothing about auth, rate limits or fallback when an edition is missing.

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 identity of the index, then usage triggers, then the default-period rule, so the important scoping information arrives early. The embedded Bulgarian phrases add some visual noise but each sentence still 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?

With an output schema present, return values need no explanation, and the description covers what the index is, when to reach for it, and the default period. Nothing an agent needs to invoke it correctly is 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 both parameters (period, language) are fully documented in the schema, including the YYYY-MM pattern and enum. The description's "latest edition unless a month is asked for" restates the schema's period default rather than adding new semantics, so 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?

It names a specific resource (the monthly Realistimo index of average asking prices per m² in Bulgaria's largest cities) and enumerates its contents (MoM/YoY change, top rising and falling квартали). This clearly distinguishes it from estimate/deal-cost siblings, but it never differentiates itself from the close sibling realistimo_market_stats, leaving some overlap to inference.

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 supplies concrete triggering phrasings ("как се движат цените на имотите", "пазарен индекс", "цени на имоти за септември") and a default rule ("The latest edition unless a month is asked for"). It stops short of stating when NOT to use it or naming market_stats as the alternative, so it is context-rich but without exclusions.

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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: statistics come from live listings, cover both sale and rental (via the example queries), and prices are quoted in euros – all operational details an agent cannot read off the annotations.

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 the metric inventory are front-loaded in the first sentence, with the query examples following as supporting evidence. It is dense but not padded; the enumerations are long yet each item maps to an actual output field, so little could be cut without losing 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?

For a 5-parameter, 3-enum tool with a full schema and an output schema, the description supplies context the structured fields cannot: data provenance (live listings), currency (euros), and the breadth of statistics returned. The one missing element is explicit sibling routing against realistimo_market_index and realistimo_estimate_price.

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 every parameter, including the location syntax, room-count semantics and the propertyType enum glosses; baseline is 3. The description reinforces the geographic scope ('an oblast capital … or one of its квартали') and implicitly the SALE/RENT split through its examples, but adds little the schema does not already say.

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?

It states a specific verb and resource – asking-price statistics derived from Realistimo's live listings – and enumerates the returned metrics (price/m², P10–P90, median, listing counts, price-cut share, 12-month trend, rental yield, sales/mortgage counts). That is far more specific than a title restatement. It does not, however, explicitly distinguish itself from siblings like realistimo_market_index or realistimo_estimate_price, so it stops 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?

Four concrete user questions ('колко струва квадратен метър в Лозенец', 'цени на апартаменти във Варна', 'наеми в Пловдив', 'доходност от наем') clearly delimit the situations this tool serves. No exclusions or named alternatives are given (e.g. when to prefer realistimo_estimate_price for a single property), but the contextual triggers are unambiguous.

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 this is a safe read-only, non-destructive, closed-world operation. The description adds genuine scope context beyond that: price/yield are returned only 'where Realistimo publishes them', and metro/kindergarten detail is limited to Sofia квартали — useful boundaries an agent couldn't infer from the schema.

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 dense but front-loaded sentence lists what the profile contains, followed by a compact quoted example block. No filler, though the opening sentence is long enough that it borders on overload.

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 an output schema present, return values need no explanation, and the description still covers data sources, conditional availability, and geographic scope limits. Nothing an agent needs to call it correctly is 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 both parameters (location, language) are fully documented in the schema. The description adds no format or syntax detail about the location string or language enum, so the schema carries the load — the correct baseline of 3.

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 'profile of a place in Bulgaria' and enumerates exactly what it contains (location description, sale/rent counts, median asking price, rental yield, plus metro/kindergartens for Sofia квартали). This clearly separates it from aggregate siblings like market_stats or market_index, though it never names an alternative 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?

Provides concrete natural-language usage examples ('какъв квартал е Лозенец', 'добре ли е да се живее в Младост') that pin down the intended moment to call it. It gives no explicit when-not conditions or named alternative tools, so it stops short of a 5.

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