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

Annotations already declare readOnly=true, openWorld=true, idempotent=true, destructive=false. The description adds meaningful context beyond annotations: it specifies the data source endpoint (api.us.socrata.com), states that no authentication is required, and describes the breadth of the catalog. This helps the agent anticipate behavior (e.g., no auth, cross-portal scope) without repeating annotation info.

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 moderately sized and front-loaded: the primary action and scope come first, followed by return fields and follow-up usage. Every sentence carries useful information—scope, returned data, downstream usage, and endpoint/auth. It avoids redundancy and reads efficiently, though it is a bit dense with multiple clauses.

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 search tool with seven parameters (all optional), an output schema, and annotations, the description is nearly complete. It covers the purpose, the catalog scope, the return set, and how to proceed with results (domain+id for other tools). It does not mention pagination edge cases or potential error conditions, but the schema covers parameters (offset/limit) and output schema exists. The follow-up guidance adds valuable context for the agent's decision-making.

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?

The input schema has 100% description coverage for all seven parameters, each with examples and types. The description does not add substantial parameter-level detail beyond summarizing that filters can be by free-text, domain, category, or tags. Since the schema covers everything, the baseline of 3 is appropriate; the description only slightly reinforces the role of parameters in the search.

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 states a specific verb (Search) and resource (Socrata Discovery API), and elaborates on the scope: a single cross-portal catalog covering thousands of government/civic open-data portals. It distinguishes this search tool from siblings like socrata.datasets.detail and socrata.datasets.query by noting that it returns dataset identifiers and points to follow-up tools for metadata or querying.

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?

It explicitly advises the agent to use the returned domain + id with socrata.dataset_metadata or socrata.query_dataset, thereby indicating the intended next steps after search. It does not explicitly state when not to use this tool, but the workflow guidance makes the usage context clear. The mention of 'free-text query, portal domain, category, and/or tags' also tells when it's appropriate (searching) versus retrieving specific datasets.

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