flatin.pt — Portuguese property taxes

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

With no annotations, the description carries the full burden. It discloses that VPT is the tax authority's valuation and instructs to ask the user, which is useful. However, it does not describe the output format, edge cases (e.g., invalid municipality), or any side effects, leaving some ambiguity for a calculation tool.

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 sentences with no fluff. It front-loads the core purpose and then adds the key caveat about VPT. Every word 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?

For a simple 2-parameter tool with no output schema, the description covers the essential aspects: what is computed, for which property type, and the crucial input constraint. It is adequate for an agent to call the tool correctly, though it could mention the return value or dependence on an urban rate.

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. The description adds valuable meaning by clarifying VPT as a tax authority valuation, not purchase price, and telling the agent to ask the user for it. This goes beyond the schema's short description and directly affects parameter handling.

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 function: computing yearly IMI for an urban property given VPT and municipality, at the urban rate. It clearly distinguishes from siblings like imi_rate (rate), imt_calculate (IMT), and request_consultation by focusing on annual cost calculation.

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 gives an important input guidance (VPT is not purchase price, ask the user) but does not explicitly state when to use this tool vs alternatives like imi_rate. Usage is implied by the function description, but no exclusions or alternative routing is provided.

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 disclosure burden and does useful work: it names the source (Autoridade Tributária portal), claims verification across all 308 municipalities, and discloses that per-parish municipalities return an explanatory answer instead of zero. It does not spell out the rate's format or year, but the core behavioral edge case is covered.

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 short sentences, with purpose and input format front-loaded, provenance/verification in the middle, and the special-case behavior last. Every sentence contributes unique information and there is no 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?

For a one-parameter lookup with no output schema, the description covers what the tool returns, the required input, the data source, reliability, and an important edge case. A minor gap is that the rate value's representation (e.g., percentage vs decimal) is left unspecified, but this does not block correct invocation.

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%, and the schema already states that the municipality may be a name or four-digit code with examples. The description repeats that input capability without adding new semantic detail, so a baseline 3 is appropriate.

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 identifies the resource precisely ('yearly property tax (IMI) rate in one Portuguese municipality') and the accepted input forms. It does not explicitly contrast itself with siblings like imi_annual_cost or imt_calculate, but the word 'rate' and the tax type make the primary purpose unambiguous.

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 context of when to use the tool is implied: when an agent needs the IMI rate for a single Portuguese municipality. There is no explicit when-not-to-use guidance or reference to alternatives, nor any mention that imi_annual_cost should be used for cost rather than rate.

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. It discloses that returns are in cents and formatted in euros, and that it includes the source of the tables, which is useful. However, it does not reveal the actual return structure (e.g., whether it returns an object with breakdown or just a total) or any assumptions beyond 'primary_home' and 'buyer_is_young'. The mention of official tables adds credibility but lacks detail on edge cases (e.g., what happens for non-first-home purchases).

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 concise and front-loaded with the key purpose, then adds relevant detail about the tables and young buyer discount. It is a single sentence that covers scope, inputs, and outputs without redundancy. The only minor inefficiency is the phrase 'what buying a home in Portugal costs on top of the price' which is slightly wordy but useful.

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 tool with 4 parameters, high schema coverage, and no output schema, the description is reasonably complete. It explains the purpose, the inputs (via context), the outputs (cents and euros, source), and identifies the key variant (young buyer scale). It could be improved by explicitly stating how the result is structured (e.g., a breakdown) and any limitations (e.g., does not include other taxes), but for the complexity level, it is adequate.

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 schema already describes each parameter. The description adds the value of mentioning the reduced scale for young buyers, which maps to the 'buyer_is_young' parameter, and confirms 'primary_home' is for habitação própria. However, it does not add format details beyond the schema (e.g., how to represent property value with decimals) nor clarify the interaction between 'primary_home' and 'buyer_is_young' beyond what is in 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 clearly states the tool calculates the extra costs of buying a home in Portugal, specifically listing IMT, stamp duty, and deed/registration costs. It also distinguishes itself from sibling tools by mentioning official 2026 tables and the reduced scale for young buyers, making its purpose and scope immediately clear.

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 implies this tool is used for upfront purchase costs (IMT, stamp duty, deed) versus the sibling tools like imi_annual_cost (annual property tax) and imi_rate (tax rates). However, it does not explicitly state when to use this tool over the alternatives, nor does it mention any exclusions, such as not including notary fees or other taxes.

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 behavioral disclosure burden. It usefully states that the request is submitted by the person, not on their behalf, preventing the agent from assuming the tool performs the submission. It does not mention potential side effects or external navigation, but for a simple return-link tool this is sufficient.

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 sentence front-loads the purpose and immediately states the key behavioral caveat ('not on their behalf'). Every part of the description earns its place, with no unnecessary verbosity.

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 description identifies both return values—the form link and GDPR consent text—and clarifies that the user submits the request. For a one-parameter tool with no output schema, this covers the essential information. Only minor details such as how to present the consent text are 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?

The input schema already documents the language parameter, supported values, and default with 100% coverage, so the baseline is 3. The description adds the 'in the user's language' context but no substantive new parameter semantics beyond what 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?

The description states a specific verb and resource: putting the user in touch with a licensed real estate agency in Portugal. It also names concrete outputs—the form link and GDPR consent text—which clearly distinguishes it from the sibling tax/fee calculation 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?

The description gives no explicit guidance on when to use this tool versus alternatives, nor does it mention sibling tools or exclusion conditions. An agent must infer from the sibling names that this is the consultation option, but the description itself does not provide selection criteria.

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