list_tables

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

Annotations already provide readOnlyHint=true, destructiveHint=false, idempotentHint=true. Description adds context: underlying SQLite engine, pattern filter hides internal tables, empty result meaning, and error when no trace loaded.

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?

Front-loaded with core purpose and read-only note. Structured into clear sections: use cases, parameter details, results, errors. Every sentence adds value without redundancy.

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?

No output schema, but description covers return expectations (empty result), prerequisites (load_trace), and edge cases (stdlib modules need include). Sufficient for a listing tool with one optional parameter.

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 describes pattern as optional string with GLOB filter. Description adds: examples ('chrome_*', 'slice*'), default behavior (hides internal tables), and practical usage hints.

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?

Description clearly states 'List tables and views in the loaded trace. Read-only.' It uses a specific verb ('list') and resource ('tables and views'), and distinguishes from sibling tools like execute_sql and list_stdlib_modules.

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 tells when to use (exploring trace, verifying table existence), when not to use (known stdlib modules – use execute_sql), and error handling (no trace – call load_trace first). Also clarifies the tool is not a SQL function.

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