get_trace_stats

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

With no annotations provided, the description discloses key behavioral traits: different statistics based on DB size (≤500K vs larger) and handling of saved vs live databases. It does not mention permissions or performance impact, but covers the main behavioral aspects.

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?

Three succinct sentences, each adding meaningful information. No fluff, and the most critical point (different stats based on DB size) is front-loaded.

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?

Given no output schema, the description explains return value differences (p50/p95/p99 vs count/avg/min/max). For a tool with two optional parameters, this is adequate for an agent to understand what to expect.

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% with descriptions for both parameters. The description adds value beyond the schema by explaining when to omit 'since' and the default for tsc (telegraphic compression).

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 it retrieves CUDA and host operation statistics, specifying different aggregation methods for small vs large databases (p50/p95/p99 vs count/avg/min/max). It also clarifies it works with both live and saved databases, differentiating it from sibling tools like get_causal_chains or get_stacks.

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 provides guidance on when to omit 'since' for saved databases, which is helpful. However, it does not explicitly state when to use this tool over alternatives, though the sibling tool names imply distinct purposes.

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