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.