adw.adw_901Is US housing affordability running ahead of the construction/supply response, signaling quarter-ahead pressure on homebuilders? Updates: monthly.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Optional: return a daily HISTORY series of the last N days (up to 5 years of real archived data) instead of the current snapshot. History requires Gold tier; without it, the current snapshot is returned. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so safety is covered. The description adds useful behavioral context: monthly update cadence and the quarter-ahead leading nature of the indicator. However, it does not disclose return format, units, or any other operational details beyond what the schema already states.
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 compact and front-loaded, with only one substantive sentence plus an update frequency note. It avoids fluff, though the question format is slightly unusual and could be seen as less direct than a standard imperative description.
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 only one optional parameter and no output schema, the tool is fairly simple. The description conveys the indicator's meaning but does not clarify the response structure or how to interpret values. This leaves some ambiguity for an agent, so it is adequate but not fully complete.
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%, and the 'days' parameter is well-explained in the schema. The tool description itself adds no parameter-level insight, so 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 clearly identifies the tool's purpose: assessing US housing affordability relative to supply/construction response, with a forward-looking homebuilder pressure signal. Although phrased as a question rather than a standard verb+resource, it provides specific substantive meaning and distinguishes this indicator from generic data pulls.
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?
No guidance is given on when to use this tool versus alternatives. The description mentions monthly updates but does not specify contexts, exclusions, or sibling-tool comparisons. An agent has no basis for selecting this over the hundreds of related adw tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
With 318 tools named adw.adw_###, agents cannot tell them apart without reading full descriptions. Multiple tools cover the same domain (e.g., at least three USD strength scores: adw_055, adw_250, adw_580; four supply-chain stress scores: adw_009, adw_019, adw_020, adw_547), making misselection highly likely.
The vast majority follow a consistent numeric ID pattern (adw.adw_###), but a small set breaks this with descriptive snake_case names (adw.catalog, adw.sample, adw.county_cancer, etc.). The numeric IDs are predictable but convey no semantic meaning, mixing with the few named tools and creating moderate inconsistency.
318 tools is far beyond any reasonable scope for an intelligence server; even the largest sophisticated APIs rarely exceed 50. This extreme count suggests poor curation and will overwhelm agents with choice, making efficient tool selection impractical.
The server covers an extremely broad range of domains (crypto, macro, supply chain, healthcare, climate, county demographics), and includes discovery tools like adw.catalog and adw.sample. However, the surface is redundant and not systematically complete—many overlapping indices exist while other potentially valuable operations (e.g., raw data export, historical trend queries) are missing, leaving moderate gaps.