observedRelationships

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe read operation. The description adds that it is 'empirically observed' from stored queries and that non-equi joins are excluded, which is useful context. However, it doesn't disclose details like whether results are paginated, how support counts are computed, or whether the catalog must be fresh. With annotations covering the safety profile, a 3 is appropriate.

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?

Two sentences with zero waste. The core purpose is front-loaded, and the alternative tool is named in the second sentence. Every word 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?

The tool has an output schema, so the description needn't explain return values. The description covers purpose, scope, exclusions, and the alternative tool. The only minor gap is that it doesn't mention whether the results are limited to the current catalog or whether the catalog needs to be populated, but given the output schema and annotations, this is nearly complete.

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 100%, so the schema already documents all four parameters. The description adds the context that the tool returns support counts and contributing query IDs, which helps understand the minSupport parameter's meaning, but it doesn't add syntax or format details beyond what the schema provides. Baseline 3 is correct when the schema does the heavy lifting.

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 states a specific verb ('Discover'), a specific resource ('empirically observed equi-join column pairs from stored queries'), and the output includes support counts and contributing query IDs. It also explicitly distinguishes itself from findJoinPaths, which is a sibling tool, by noting that findJoinPaths is for declared/combined paths and that non-equi joins are excluded. This makes the tool's purpose unambiguous and differentiates it from siblings.

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 explicitly says 'Use findJoinPaths for declared/combined paths between endpoints; non-equi joins are excluded.' This provides clear when-to-use and when-not-to-use guidance, naming the alternative tool and the condition that selects it. The connection parameter also instructs to call listConnections for valid names, which is a usage guideline.

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