StartApiTrace

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

Annotations only give the generic profile (readOnly=false, openWorld=true, non-idempotent). The description goes well beyond them: breakpoints are 'silent+continue-on-hit', there is a 200-BP cap that surfaces an error listing per-module counts, native vs. Python return-hook fallback is described, and the return summary shape is enumerated. That is meaningful operation-level disclosure.

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-loads the purpose and the RunApiTrace handoff, then uses a clean Args block with the return summary last. The custom_targets_json entry is dense but each sentence carries real information; only minor trimming is possible.

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 16-parameter session-setup tool with no output schema, the description covers the core mechanics and return summary well, but seven parameters are left entirely undefined and no prerequisite (debuggee must already be initialized/attached) is stated. Adequate, with clear gaps for a tool of this complexity.

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 0%, so the description carries the full burden, and it documents 9 of 16 params with defaults, examples and non-obvious semantics (empty-string fallbacks for modules_json/filter_json, custom_targets_json selection rules and kind='import-resolver'). Gaps remain for caller_filter, max_out_bytes, capture_returns/callstack, decode_string_args, max_callstack_frames and collapse_nested_families, though several are guessable from their names.

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 first line gives a precise verb+resource ('Set up ... an API call trace session') and immediately bounds the scope with '(but do not yet run)'. It also distinguishes itself from the sibling RunApiTrace by naming it and stating what that tool does. An agent can pick this over RunApiTrace/StopApiTrace without opening any 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?

It clearly routes the caller: setup happens here, execution happens in RunApiTrace. The max_targets error path also tells the caller how to recover (narrow the filter). It stops short of stating prerequisites (InitDebuggee/AttachToProcess appear as siblings but are never referenced) or when not to use it.

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