Get slice time/flow breakdown

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

The description discloses statelessness, the predicted-vs-observed check, the 'clamped' throttling concept, and failure mode degradation to {"available": false, "reason": ...}. This goes well beyond the readOnlyHint annotation and provides critical behavioral context.

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 well-structured: a summary sentence, a detailed breakdown of return values, and a clear edge-case note. Every sentence adds value and the length is appropriate for the tool's complexity.

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?

With no output schema and no parameters, the description fully carries the burden of explaining what the tool returns: per-role metrics, global distributions, per-layer aggregates, prediction_check, and degradation behavior. It also notes the fork-build prerequisite. This is complete for making an informed tool call.

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?

The tool has 0 parameters, so the baseline is 4. The description adds no parameter-specific semantics (none needed) but does explain what the returned data covers, which is useful given no output schema.

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's purpose: 'Per-feature breakdown of the last slice' and explicitly answers 'which feature is the time hog' directly, distinguishing it from trial slicing and sibling tools like get_slice_status or get_slice_warnings.

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 provides clear context: use this to identify time-consuming features instead of trial slicing. It also mentions degradation conditions (fork builds without breakdown emission, no valid slice). However, it does not explicitly name alternative tools like get_slice_status or get_slice_warnings, so exclusion guidance is implicit rather than direct.

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