slice_descendants_breakdown

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

Annotations indicate read-only and idempotent. The description adds significant behavioral detail: echoes summary_scope, applied_filters, missing_root_ids; explains each column (e.g., do not sum inclusive_total_ms across depths, self_ms clamped at zero, first_ts_ns in raw nanoseconds, incomplete_descendant_count excludes dur<0). Root slices are omitted from summary. These details go beyond 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?

The description is a single dense paragraph but front-loads the purpose and efficiently covers all aspects. Could be slightly improved with bullet points for the list of parameters and return columns, but it is not overly verbose and every sentence adds value.

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?

No output schema, so the description fully documents the return structure: columns, their meanings, and special handling like clamping and incomplete counts. It also covers optional parameters and the summary metadata. Given the complexity of recursive expansion and many columns, this is complete.

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%, but the description enriches each parameter with defaults and context: limit defaults to 100 capped at 5000, max_depth defaults to 8 and must be >0, min_dur_ms defaults to 1 ms, include_args boolean, max_string_len must be >0 if set. It also notes that slice_ids accepts numbers or numeric strings and trace_id can be omitted for active trace.

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 performs recursive child-slice expansion under given slice.id roots, aggregated per (depth, name) group. It distinguishes from siblings like chrome_main_thread_hotspots and execute_sql by specifying its use case: drilling into long tasks after those tools return a slice id.

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: after chrome_main_thread_hotspots or execute_sql returns a slice id, and that it avoids writing recursive CTEs. Does not explicitly list when not to use, but the context is clear given the required parameter and sibling tools.

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