sql_Retrieve_Cluster_Queries

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

Annotations declare readOnlyHint and idempotentHint as true, indicating safe read-only behavior. The description enhances transparency by detailing the performance categorization logic (CPU, skew categories) and the metrics available for sorting. It also describes the output composition (SQL text, metrics, categories). No contradictions with annotations.

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 but well-structured with bold headers and bullet points. Each section serves a purpose: purpose, capabilities, strategies, metrics, categories, workflow, limits, output. A bit verbose but efficiently organized. Could be more concise in some sections, but nothing is wasted.

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 the tool's complexity (3 parameters, no output schema, rich behavioral context), the description is thorough. It covers input parameter usage, output composition (SQL text, metrics, categories), and behavior (sorting, categorization). It also places the tool in a workflow with siblings. Without output schema, the description fully details return values.

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 0% (description does not document parameters in structured format), but the description extensively compensates. It explains the 'metric' parameter with available values and default, implies 'cluster_ids' by context, and covers 'limit_per_cluster' in the query limit strategy. The default values and sorting options are clearly documented, adding significant meaning beyond the schema.

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 retrieves actual SQL queries and performance metrics from specific clusters for pattern analysis. The bolded title and first paragraph establish the specific verb-resource pair (retrieve queries from clusters) and distinguish it from sibling tools like sql_Analyze_Cluster_Stats, which likely focuses on cluster-level statistics rather than individual query details.

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 guidance on when to use this tool: after cluster identification from sql_Analyze_Cluster_Stats, as part of a typical optimization workflow. It also details query selection strategies by various metrics and a query limit strategy. It does not explicitly mention when not to use or name alternatives beyond the workflow context, but the 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.