Greca House: Greek Property

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

Annotations already establish readOnly/idempotent/non-destructive, so the description is free to add what they cannot: the data provenance (Greca House's own listings' ASKING prices, a dated snapshot, reported with sample sizes) and the explicit caveat that it is not a market index. It also warns the agent not to inject remembered 'current market' figures, which is actionable behavioral guidance beyond any structured field.

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 triggering use case and the guidance sentences each earn their place. However, the provenance point is stated twice in near-identical wording ('Answers from Greca House's dated research snapshot of its own listings' asking prices...' followed by 'A dated snapshot of Greca House's own listings' ASKING prices...'), which is real 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?

With an output schema present, return values need not be explained, and annotations cover the safety profile, so the remaining burden is scope and source. The description handles both plus its limitations, but never states how old the 'dated snapshot' is or whether sample sizes can be zero, leaving the agent unable to judge staleness or reliability.

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 67%: areas and language are described in the schema, but budget_eur has no schema description. The description compensates by explaining what budget_eur means semantically (it answers what a given budget buys) and by giving example values, which is more than the schema 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?

States a specific verb and resource ('compare asking prices per square metre between Greek areas') and two concrete query shapes: area-vs-area and budget-vs-area. It also explicitly distinguishes itself from a whole-market transaction-price index, so an agent can tell it apart from get_greece_market_research and the listing-search 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?

Gives explicit when-to-use triggers (Kolonaki vs Glyfada, or 'what does €250k/€400k/€800k buy') and an explicit when-not list: forecasts, predicted appreciation, next-year growth, time-series trends, whole-market future prices. Alternatives are not named by tool name, but the exclusion categories route the agent unambiguously away from this tool for those questions.

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?

Goes well beyond the readOnly/idempotent annotations by disclosing critical guardrails: never invent professional fee percentages, professional fees only from written quotes, do not produce a generic 'typical all-in' range, and never apply announced_not_in_force rates as current law. It also flags 'not legal or tax advice' and requires preserving the calculator link and assumptions.

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 usage trigger and keeps everything in a single efficient paragraph, but repeats the 'professional fees only from amounts the user gives' rule twice, which is redundant emphasis rather than new 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 an output schema present, return values need not be described, and the description covers the computation, its guardrails, assumptions to preserve, and the announced-vs-in-force rate rule. Coverage is strong, though the meaning of registered_in_cadastre and the language enum is left to the 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 coverage is 60%, and the description adds real meaning beyond the schema: tax is due on the higher of price vs objective value (objective_value_eur) and professional_quotes_eur must come from written, VAT-inclusive quotes. It does not explain the language enum or registered_in_cadastre semantics, leaving a small 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 verb and resource ('estimate buying costs ... on top of the price to buy a resale property in Greece') and enumerates the components computed (transfer tax, municipal surcharge, Cadastre registration, notary's scale fee). This clearly distinguishes it from the sibling search/research tools.

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 an explicit trigger ('use this when the user asks how much it costs on top of the price to buy a resale property in Greece') and a clear boundary that professional fees enter only from user-supplied amounts. It does not explicitly name or rule out sibling tools, but the usage condition is 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 readOnlyHint, idempotentHint, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context the annotations cannot convey: the data is a dated snapshot of Greca House's own listings at ASKING prices, not transaction prices, plus an anti-hallucination instruction. It stops short of richer detail (e.g. how stale the snapshot is, pagination), so 4 rather than 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?

Four dense sentences, front-loaded with the use case before the exclusions, and every sentence carries load (scope, provenance, exclusions, anti-hallucination rule). It is longer than typical but not padded, though the final 'other sources may be cited' sentence is slightly tangential to tool selection.

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; it instead supplies the things structured fields cannot — data provenance, snapshot nature, and scope boundaries versus forecasts and whole-market indices. An agent has everything needed to select and invoke it correctly.

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 only 50% (the topic enum has no per-value description), and the description compensates by spelling out the topics in prose: regional overview, Athens neighbourhood medians, budget windows, method, CSV downloads — mapping cleanly onto the enum values. The language parameter is left to the schema, which already documents it, so the description adds real but partial 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?

The description names a specific resource (Greca House's own asking-price research on Greek property) and enumerates exactly what it returns: regional overview, Athens neighbourhood medians, budget windows, method, CSV downloads. It also states what it is NOT (a whole-market transaction-price index), which lets an agent separate it from sibling property tools 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?

Explicit when-to-use ('when the user asks for Greca House's research on Greek property asking prices') and explicit when-not-to-use (forecasts, predicted appreciation, next-year growth, time-series trends, whole-market future prices). It even rules out filling gaps from memory and sets a condition for citing other sources, which is unusually complete routing 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, idempotentHint, non-destructive and closed-world, so the safety profile is fully covered. The description adds no behavioral traits beyond that profile (no rate limits, no auth or error behavior) and instead spends its text enumerating the return payload. Adequate but not additive beyond structured data.

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 sentences, front-loaded with the usage trigger before the payload list; no filler. The payload enumeration is somewhat long, but each item (Golden Visa classification, 3D/360° links) is a genuine differentiator an agent could cite.

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 enumerate return fields, though it does so helpfully. Nothing an agent needs to call it correctly is missing: identifier format, language options via schema, and the single-listing scope are all covered.

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 (reference with its regex and example, language with its enum) are already documented in the schema. The description restates the reference example but adds nothing about the language parameter or default behavior, 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?

Names a specific verb+resource (retrieve one Greca House listing) and pins the identifier form with a concrete example (GH-108459). It is clearly distinguishable from siblings like search_greece_properties or get_greece_market_research, which operate on sets or markets rather than a single listing.

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?

"Use this when the user asks about one specific ... listing by its reference ... usually after a search" gives an explicit trigger condition and sequencing relative to search. It stops short of naming the alternative tool (search_greece_properties) as the fallback for non-specific queries, which would make it a 5.

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 safe-read profile (readOnly, idempotent, openWorld=false), so the bar is lower, and the description still adds real context: the corpus is limited to Greca House listings, and the return payload is references, asking prices and links. The golden-visa guardrail (do not infer eligibility, applicant or permit approval) is a genuine behavioral constraint beyond the annotations, though it is repeated verbatim 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?

The scoping sentence is front-loaded and efficient, but the trailing golden_visa paragraph duplicates, word for word, the description of the golden_visa_classified_only parameter and could have been a single reference to it. That repetition costs space without adding information the agent cannot already read in the schema.

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 not be explained, and annotations cover safety; what remains is coverage and semantics, which the description addresses for scope, region vocabulary and the golden-visa caveat. The gaps are the undocumented pagination/sort/language/filter parameters, which no prose compensates for.

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 47% across 15 parameters, and the description compensates only partially: 'budget, area, type or size' maps loosely to price, area, property_type and size parameters, and the parenthetical region list mirrors the region enum. Nothing is said about deal, sort, limit, offset, language, has_media or the bedroom bounds, so roughly half the surface remains undocumented outside 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 first sentence names a specific verb (search) and resource (Greca House property listings in Greece) and immediately bounds the corpus ('Greca House's current public listings only, not every property in Greece'), which distinguishes it from the market-research, cost-estimate and detail 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?

It states when to use it ('user wants to find homes, land or commercial property for sale or rent ... within a budget, area, type or size') and gives explicit when-not exclusions (holiday rentals, hotels, travel bookings). It never routes to a sibling such as get_property_details or compare_budget_by_area, so the alternative-selection guidance is incomplete.

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