search_datasets

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

With no annotations, the description carries the burden and does reasonably well: it discloses the harvested-index dependency, enumerates what each result contains (portal, link, formats, update date), and explains the Socrata-specific domain + 4x4 handoff to another MCP. It stops short of stating result ordering, default limit, or rate/refresh characteristics of the index.

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?

Three dense sentences, front-loaded with what is searched and then what can be filtered on, with zero filler. The prerequisite and the cross-MCP handoff are packed into the same compact text rather than padded out.

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 7-parameter read tool with no annotations and no output schema, the description covers both input intent and return shape well enough to call it correctly. Minor gaps remain around result ordering, the default page size, and what happens if the index is empty or unharvested.

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?

At 71% schema coverage the schema already documents most parameters, and the description largely mirrors them (place, portal, platform family, format, last-updated). Its format enumeration is actually narrower than the schema's list, omitting json, arcgis, geopackage and pdf, so it adds little semantic value beyond the structured fields.

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 and resource — 'Search dataset titles, descriptions, tags and column names' — and bounds the corpus to harvested Socrata and ArcGIS portals in New York. It is clearly distinguishable from siblings like get_dataset_columns or find_sources, though it never names an alternative directly.

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 parenthetical '(needs the harvested index)' is a useful prerequisite an agent must satisfy before calling, and the filter list implies the intended discovery workflow. However there is no explicit when-to-use vs when-to-use-another guidance and no sibling is mentioned by name.

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