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

Beyond the readOnly/idempotent/non-destructive annotations it discloses non-obvious behavior: the first search of a connection reads the whole catalog and can be slow on a large warehouse, results are capped at 50, and reads are scoped to the user's access on the connection (default user when set). That latency and authorization context is exactly what annotations cannot express.

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 purpose is front-loaded, but the opening sentence is a run-on chain of clauses (matching rule, case sensitivity, 50-result cap, access scoping) that is hard to parse on first read. The workflow sentences are efficient, so the issue is density rather than wasted content.

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 no output schema, the description carries return semantics itself: at most 50 tables/views, each addressable by connection, database, schema and table. It omits the exact result field shape, but the downstream handoff to addReportDatasheets and sendReportMessage makes the usable output clear.

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?

Top-level schema coverage is 0% (the query and params wrappers are undescribed), and the description compensates by anchoring what query matches (table full name including database and schema, case-insensitive, any word) and that the connection type/id come from listConnections. It still does not explain the nested wrapper structure or that params is required, so it is strong but not complete.

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?

Specific verb (search) and resource (tables and views of a Snowflake or Databricks connection), with the matching rule stated: the full name database.schema.table must hold any word of the query. It is clearly distinguished from sibling searchers (searchDashboards, searchModels, searchSpreadsheets) by naming the object type and warehouse connections.

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?

Explicitly prescribes the workflow: search by the name the user gives, confirm the table with the user, add it via addReportDatasheets using connection/database/schema/table, then pass the datasheet id to sendReportMessage. It also points to listConnections for the connection type and id, so the call ordering is unambiguous.

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