load_trace

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

Annotations already declare idempotent and non-destructive. Description adds valuable context: caching behavior ('cached trace processors make repeat loads cheap'), active default trace management, and error conditions. No contradiction with annotations.

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 action and output, then uses clear sections for usage, parameters, and errors. Every sentence adds value; no fluff or 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?

Covers return value (routing summaries + trace_ids), error conditions, and behavior with multiple calls. Without an output schema, the description is sufficiently complete for an agent, though more detail on the return structure could help.

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 path and paths. The description adds usage nuance (one vs batch, active default) and caching behavior, which provides extra value beyond the schema. However, the schema already covers format and mutual exclusivity.

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 the tool loads Perfetto trace files and provides trace_id handles, distinguishing it from sibling analysis tools which consume loaded traces. The verb 'load' and resource 'local Perfetto trace files' are specific.

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?

Explicit 'Use when' and 'Don't use for' sections guide the agent to call this first for analysis sessions and avoid live capture. It also explains how other tools use the active trace and how to pass trace_id.

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