Open cursor

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

No annotation contradiction (readOnlyHint=true aligns with read-only cursor). Description adds behavioral details beyond annotations: TTL of 5 minutes, hard cap of 16 concurrent cursors, and server-side result set holding.

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 sentences, front-loaded with purpose, efficient coverage of key points without waste. Every sentence earns its place.

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?

Given output schema exists, description doesn't need return details. Covers all necessary context: what it does, how to use, constraints, and relationship to sibling tools. Complete for a read-only cursor tool.

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 coverage is 50% (only database described). Description doesn't add much parameter detail beyond schema; it mentions SQL validation and purpose but no specific syntax or constraints. Adequate but not comprehensive.

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 verb ('Open a server-side cursor') and the resource ('for a SELECT query'), explaining the purpose of paging through large result sets. It distinguishes from sibling tools like fetch_cursor and close_cursor.

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?

Provides good guidance: SQL validation from run_select, how to fetch and close, TTL and concurrency cap. Lacks explicit when-not-to-use but context is clear enough.

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