find_joinable

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

With no annotations provided, the description carries the full burden of disclosure. It does disclose a genuinely important behavioral trait: matching uses a curated key-column map rather than raw column-name equality, so results reflect a normalization layer. However, it never states that this is a read-only operation, says nothing about how large or expensive the scan is, and does not describe error behavior when the dataset_id is invalid.

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?

Two sentences, zero filler. The primary purpose comes first, and the list of keys and the curated-map caveat follow as supporting detail. Nothing could be removed without losing information.

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 three-parameter read tool with no annotations and no output schema, the description covers the core semantics and the key taxonomy. What is missing is a sense of what a result entry looks like beyond 'grouped by key' and whether limit_per_key applies per group. That roughly matches the expected baseline, but it is not complete for a dataset-discovery 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 description coverage is 67%; the dataset and column parameters are documented in the schema. The description adds real meaning by enumerating the recognized key labels (BBL, BIN, borough, census tract, FIPS, ZIP, and so on), which clarifies what 'column' will accept. It says nothing about limit_per_key (which the schema also leaves undocumented) or about how a field name differs from a key label in practice.

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 uses a specific verb-plus-resource construction: it returns datasets that share a join key with a given dataset, and it explicitly says the results are grouped by key. That is far more precise than its name 'find_joinable' alone. It does not name a sibling such as search_datasets or find_sources to contrast with, but the purpose is unmistakable.

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 phrase 'share a join key with this one' implies the use case, which is finding datasets you can join against the supplied dataset. The description gives no explicit when-to-use or when-not guidance, and it does not say to call it instead of, or after, get_dataset_columns or search_datasets. The descriptors in the input schema (dataset_id, Socrata 4x4, ArcGIS item id or URL) support the guidance that already exists implicitly.

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