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

Annotations already cover read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower; the description still adds real value by disclosing snapshot semantics ('pages stay pinned to one version') and the failure mode for oversized result sets. It does not explain how a version is obtained or what happens with an expired cursor.

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?

Four short sentences, front-loaded with the core action and no filler. The 'Oversized results require fewer rows/columns' sentence is terse to the point of being cryptic about the actual remedy.

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?

An output schema exists, so return values need not be described, and pagination/versioning is at least acknowledged. For a 10-parameter tool with zero schema descriptions, however, an agent still lacks enough guidance to set sort, limit, cursor, table, or workspace_id correctly.

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% across 10 parameters, so the description carries the full burden, yet it only alludes to columns, filters (equality), and version pinning. Sort/descending, cursor pagination, limit bounds, table vs dataset_id selection, and workspace_id are left entirely unexplained.

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 concrete verb+resource ('Read exact typed rows from one dataset table') and scopes it with optional equality filters and column selection. It implicitly separates itself from browse/exploratory reads and SQL tools ('No SQL'), but never names the sibling browse_dataset_rows, so the differentiation is inferred rather than stated.

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?

Usage context is implied ('optional equality filters', 'No SQL or credentials', 'Oversized results require fewer rows/columns'), which tells the agent this is a bounded, filter-based read. It never says when to choose this over browse_dataset_rows or query_dashboard, nor when the version/cursor parameters are required.

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