schemaBrief

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

Annotations already cover readOnly, openWorld, idempotent, and non-destructive behavior. The description adds valuable context: it returns a 'broad plain-text map' (indicating output format) and implies a fallback to full schema when terms don't match (via the parameter description). It doesn't contradict annotations and enhances understanding of the tool's role as a discovery entry point.

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 first sentence states the core purpose, and the second conveys output type and recommended follow-ups. The description is front-loaded with the key action and scope, then efficiently routes the agent to next steps.

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?

For a discovery tool with rich annotations, no output schema, and 4 parameters, the description fully covers purpose, usage, output format, and next steps. It also leverages parameter descriptions for connection validation and maxTables. Nothing critical for correct invocation is missing.

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 75% (terms, maxTables, connection have descriptions; schema does not). The tool description doesn't add parameter-specific meaning beyond what the schema already provides. Baseline for high coverage is 3; the description's mention of 'names are unknown' reinforces the terms parameter but doesn't add new semantic detail.

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 ('candidate tables and views across a schema'), and a clear condition ('when their names are unknown'). It also differentiates from siblings by mentioning follow-ups (queryContext, describeTable) and implies searchObjects/listTables are for known names. This is a distinct, non-tautological purpose.

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?

Explicitly states the condition for using this tool ('when their names are unknown') and gives concrete follow-up actions ('follow with queryContext for multi-table authoring detail or describeTable for one known object'). This directly addresses when to use this tool versus alternatives, leaving no ambiguity.

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