trace_tables

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

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds a meaningful behavioral caveat: recordings retain their .trace only when KEEP_TRACE=1, which affects whether this tool can be used at all. It stops short of saying what happens when the trace is absent or not kept.

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?

The definition is a single front-loaded sentence with no wasted wording. The KEEP_TRACE=1 clause is relevant but slightly terse and could be mistaken for a condition on this tool rather than on trace retention.

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 read-only listing tool with an output schema, annotations, and full parameter coverage, the description is complete enough to call it correctly. The main missing piece is explicit sibling routing, but the core behavior and trace-retention caveat are present.

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%, and the parameter description already explains that the trace argument can be a run name with trace_kept=true or a .trace path. The tool description does not add format or validation details beyond that. Baseline 3 is appropriate when the schema covers the single parameter thoroughly.

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 and resource: it lists the data tables (schemas) contained in a .trace recording. This distinguishes it from query/count siblings by output type, though it does not name those siblings explicitly. The purpose is clear without opening the schema.

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?

Usage is only implied: an agent can infer this is a discovery step before querying a trace, but the description gives no explicit when-to-use guidance or comparison to trace_query or trace_count. The KEEP_TRACE=1 note is a retention prerequisite rather than routing guidance.

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