Ask OpenConstruction

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does reveal that the tool grounds answers in the catalog (a useful anti-hallucination signal) and that it returns 'matching resources,' but it does not disclose failure behavior (e.g., no matching resources), the nature of the answer format, whether it executes a retrieval/LLM pipeline, or any auth/permission requirements. For a question-answering tool this is thin on behavioral detail.

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 a single efficient sentence of eight words with no filler. The action verb 'Answer' is front-loaded and the key qualifier 'catalog-grounded' appears early. 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 one-parameter tool with no output schema and no annotations, the description covers the purpose and the nature of the query adequately. Yet it omits response characteristics (no output schema exists to fill this gap), no-match behavior, and any distinction from similarly-purposed siblings. These gaps mean the description alone is not fully sufficient for confident, 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 description coverage is 0%, so the description must compensate fully for the single 'query' parameter. It does add some meaning by characterizing the query as a 'catalog-grounded question,' which helps an agent understand the expected input is a natural-language question about the catalog. However, it does not elaborate on acceptable question scope, expected phrasing, or how the query is interpreted against the catalog, leaving the parameter semantics only partially enriched.

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 ('Answer') with a qualified resource ('catalog-grounded question') and a concrete outcome ('matching resources'). It communicates that the tool performs natural-language question answering against a catalog, which is a discernible purpose. However, it does not explicitly differentiate itself from sibling tools like search_resources or find_datasets, which could plausibly overlap in returning matching resources.

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?

There is no guidance on when to use this tool versus alternatives such as search_resources, find_datasets, or get_resource. The phrase 'catalog-grounded' only implicitly suggests a use case (questions grounded in catalog data), but there is no explicit condition for selection, no exclusions, and no mention of when the structured search tools would be preferable. An agent has to guess at the routing decision.

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