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

Without annotations, the description fully discloses the tool's behavior: it is READ-ONLY, sandboxed, limited to one SELECT (or WITH...SELECT), prohibits certain SQL commands, restricts file access to curated paths, enforces join keys, caps results, and defines NULL semantics. It also mentions error handling. This is comprehensive and leaves no ambiguity about side effects or constraints.

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 long and detailed, but every sentence provides essential information about usage, constraints, and semantics. It is structured with dashes and semicolons to separate distinct points, making it scannable. While not terse, the density of critical details justifies the length; no significant redundancy is present.

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?

The description covers all necessary context: the type of query, prerequisites, restrictions, join-key requirements, result limitations, NULL handling, and error behavior. It also mentions the 'truncated' flag, which aligns with the output schema (though the output schema is not shown explicitly). An agent has sufficient information to use the tool correctly and anticipate outcomes.

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 schema only provides types and defaults for 'sql' and 'limit'. The description adds context by specifying the acceptable SQL form (one SELECT or WITH...SELECT) and mentions result caps, which indirectly clarifies the limit parameter. However, it does not explicitly tie 'limit' to row/byte caps or explain 'sql' beyond the allowed syntax. The description adds moderate value beyond the schema, so it scores slightly above baseline.

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 the tool's purpose: running cross-dataset analytical SQL queries that per-topic filters cannot express. It uses the verb 'Run', specifies the resource (analytical SQL), and distinguishes it from per-topic query_dataset filters, making its role unambiguous.

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 description provides explicit usage guidance: it names the prerequisite (call link_tables first, use only read_parquet on returned paths), restrictions (no direct file paths, no DDL/DML/COPY/ATTACH/INSTALL/PRAGMA/SET/CALL), and behavioral expectations (joins use link_keys, results are capped, NULL means suppressed). This gives an agent clear instructions on when and how to invoke the tool.

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