describe_schema

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It clearly states the tool is a read-only introspection operation (describing schema), which is useful. However, it doesn't disclose details like whether the output is truncated, how many tables are returned when omitted, or whether it requires any special permissions. The core behavior is transparent enough for a schema-inspection tool, but some edge-case behavior is unspecified.

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 tool's function and scope, and the second provides a critical usage directive. The imperative 'Always call this before writing SQL' is front-loaded and actionable.

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 simple introspection tool with one optional parameter and an output schema, the description is nearly complete. It covers what the tool does, when to use it, and the parameter semantics. The only minor gap is not describing the output format in prose, but the output schema exists and the description's directive is sufficient for an agent to use it correctly.

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 already documents the single parameter well (table to describe, omit for all tables), and the description reinforces this by saying 'for one table or all tables.' The description adds the crucial context that omitting the parameter means all tables, which aligns with the schema's default null. Since schema coverage is 100% and the description adds a clear behavioral nuance, this is 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 states a specific verb ('Describe') and resource ('columns, types and foreign keys') for either one table or all tables. It clearly distinguishes itself from siblings like list_tables (which lists table names) and run_query (which executes SQL).

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 instructs when to use this tool: 'Always call this before writing SQL -- do not guess column names.' This is a clear usage directive that tells the agent to invoke this tool as a prerequisite before run_query, and it implicitly contrasts with list_tables by focusing on schema details rather than table names.

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