list_tables

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint, and openWorldHint. Adds value by explaining SQLite engine, behavior of pattern parameter hiding internal tables, empty result handling, and error when no trace loaded. No contradictions.

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?

Description is well-structured with clear sections (Use when, Don't use for, Parameters, Empty result, Errors). Every sentence adds value, no fluff. Appropriately sized for the tool's complexity.

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?

Despite no output schema, the description covers return behavior (empty result) and error conditions (no trace loaded). It also explains the underlying SQL engine limitation, making the tool's role clear in the larger system.

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 100%, so baseline is 3. Description adds meaningful details: pattern is a GLOB filter with examples, trace_id is optional and defaults to active trace. This provides context beyond the schema descriptions.

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 'List tables and views in the loaded trace. Read-only.' It uses a specific verb and resource, and distinguishes itself from siblings 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 states when to use (exploring unfamiliar trace) and when not to use (known stdlib modules, avoid calling tool name in SQL). Mentions alternative execute_sql with INCLUDE PERFETTO MODULE.

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