Moradas — Portuguese addresses & postal codes

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

With no annotations, the description carries the burden of disclosing behavior. It makes the read-only nature clear through 'Look up' and enumerates the returned fields, including that street coverage is part of the result. It doesn't cover invalid input behavior or response shape, but for a simple lookup the core behavior is transparent.

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 sentence front-loads the verb and resource, gives a concrete example, and lists the output fields. No filler or redundancy.

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 read-only lookup with no output schema, the description covers input format (with example) and output contents (place hierarchy and streets). The only gaps are lack of explicit differentiation from resolve_postal_code and any error/edge-case information, but the tool is otherwise self-explanatory.

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 single cp7 parameter is already documented as 'Postal code NNNN-NNN'. The description adds only a concrete example and the CP7 term, which is helpful but does not substantially extend the schema's meaning.

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 opens with a specific verb ('Look up') and names the resource (Portuguese postal code CP7 with an example), then lists the returned information (localidade, concelho, distrito, streets). It is clear and concrete, though it does not explicitly differentiate itself from the sibling resolve_postal_code.

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 intended use is implied: use this when you have a CP7 like '1000-098' and want locality/district/street information. However, it gives no explicit when-to-use guidance, no prerequisites, and no comparison to resolve_postal_code or suggest_address.

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 does the work: it discloses the return shape (resolved address or null, plus the street's postal-code segments) and the input precondition that makes resolution possible. Auth/rate-limit behavior is unstated, but for a read-only resolution call the key behavioral facts are 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 sentences, no filler: purpose first, then the key parameter constraint, then the return contract. Every clause carries information an agent needs.

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?

Although there is no output schema, the description spells out the return values including the null case and the auxiliary postal-code segments list, and documents how to obtain valid input. Nothing needed to call this 2-parameter read tool 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 coverage is 100% so the baseline is 3, and the description earns an increment by adding provenance and validity info for art_id (must come from suggest_address, 0 is unresolvable) that the schema's terse 'Street id from suggest_address' does not fully convey.

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 (resolve) and resource (7-digit postal code / CP7) scoped to a street + door number, which is clearly distinct from suggest_address (id lookup) and postal_code_info. The parenthetical 'CP7' pins down the exact artifact, so an agent knows what it gets back.

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?

Explains the prerequisite chain explicitly: art_id must come from suggest_address, and art_id 0 (a locality/municipality) cannot be resolved, which is an effective implicit exclusion. It does not name an alternative when the user already has a postal code, but the sequencing guidance is clear.

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 and delivers well: it enumerates the returned fields, explains the meaning of a null cp7, notes that a lowercase municipality prefix returns the place itself first (art_id 0), and surfaces the corrected:true flag. It stops short of error conditions, permissions or rate limits, so it is strong but not exhaustive.

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 purpose and input format before moving to return shape and cross-tool workflow. Every sentence carries information, though the packing of multiple edge cases into single sentences makes it slightly run-on rather than crisply structured.

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 and no annotations, so the description must cover return values and it does, listing each returned field and its edge-case semantics. Combined with the input format guidance and the follow-up workflow to resolve_postal_code, an agent has everything needed to call 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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning: it explains what 'q' accepts in prose and examples, and explains the otherwise opaque art_id returned when there is no street-level match. The count parameter is left to the schema, which is adequate.

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 opens with a specific verb and resource ('Autocomplete a Portuguese address or postal code') and immediately distinguishes itself from resolve_postal_code by naming the condition under which that sibling should be used instead. An agent knows exactly what this tool returns (street, localidade, concelho, distrito, cp7) without opening a 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?

It states accepted input forms with concrete examples ('av liberdade lisboa 196', '1000-098') and explicitly routes to the alternative tool: 'When cp7 is null ... call resolve_postal_code with art_id and the door number.' It also describes behavior for municipality prefixes and typo correction, leaving little to inference.

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 and does so: it discloses per-item resolution behavior, rate limiting (~50 per 10 seconds per IP, N items = N requests), result ordering, and the full status taxonomy with the exact meaning of ok/ambiguous/not_found and their cp7/suggestion values.

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 purpose and alternative routing, then progressively details statuses and limits. Dense and mostly waste-free, though the status enumeration is long enough that a reader must work through several clauses to extract the core contract.

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?

No output schema exists, yet the description fully specifies the return shape (id, q, status, cp7, suggestion), ordering, and status-dependent null values. Combined with the batch and rate-limit rules, an agent has everything needed to call and interpret this 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?

Schema coverage is 100% so the baseline is 3, but the description adds meaning beyond the schema: how each q is interpreted (door number picks exact postal code, postal code looked up as such), the echo behavior of id including null when omitted, and the returned result fields.

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 ('Check a list of Portuguese addresses in one call') and immediately scopes it as bulk-oriented. It explicitly contrasts with suggest_address for single addresses, so an agent can distinguish it from siblings without opening a 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?

Gives concrete use cases (CRM column, order import, customer base before shipping/mailing) and an explicit alternative with its trigger condition: 'For a single address use suggest_address.' Batching guidance (up to 100 items, send ~50) further directs correct invocation.

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