ParseAddr — Address Parsing & Normalization

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

With no annotations, the description carries the full behavioral burden. It conveys the tool's transformation (normalizing to canonical variants) and implies a pure, read-only operation via the dedup example, but says nothing about the output shape (single string vs list of variants), ordering, or edge-case behavior on unparseable input.

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 compact sentence with the core purpose front-loaded and an illustrative example appended. Trailing whitespace/newlines are cosmetic waste, and the parenthetical example could arguably be folded more tightly, but overall it is efficient.

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 no output schema, the description should clarify what comes back; it says 'canonical variants' (plural) but never describes the return structure or whether it is a list. Combined with no sibling differentiation, an agent has enough to call it but not to predict or disambiguate 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?

One required string parameter with 0% schema description coverage, so the description must compensate. The example ('100 main st') illustrates accepted input format, but the parameter name 'address' is the only naming signal and no constraints (single-line, no country, etc.) are given.

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 pair (expand/normalize), the resource (address), and the output form (canonical variants), plus a concrete example. It does not, however, distinguish itself from the sibling parse_address, which an agent would plausibly confuse it with.

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 a use context (deduplication and record matching), which implies when the tool is useful, but it never states when to prefer it over parse_address or what parse_address does instead. Usage is inferable rather than explicit.

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?

No annotations are provided, so the description carries the burden. It discloses the underlying engine (libpostal) and the operational context (avoids a 2-4GB RAM box and C build), but says nothing about auth requirements, rate limits, or how unparseable input is handled. Derived from real OSS internals, but incomplete on the operational profile.

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 action and output fields, followed by a usage cue. The aside about RAM and the fiddly C build is mildly conversational, but it earns its place by justifying tool selection over self-hosting.

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, so the description correctly enumerates the returned structured fields (house_number, road, unit, city, postcode, country). That covers the main gap; only the error/edge-case behavior is left unspecified.

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 0% for the single required 'address' parameter, so the description must compensate — and it does by specifying the input is a messy free-text postal address rather than pre-structured data. It adds meaningful input semantics beyond the bare 'string' 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?

States a specific verb (parse) and resource (free-text postal address) and enumerates the structured output fields it produces. The purpose is unmistakable, though it never mentions the sibling expand_address, so differentiation is left to the agent.

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 when a developer needs to standardise or parse postal addresses and does not want to self-host libpostal" gives a concrete usage scenario and even a rationale for choosing this hosted tool over a self-hosted build. It stops short of naming expand_address as an alternative or stating when not to use it.

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