Get slice time/flow breakdown

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

Beyond the readOnlyHint annotation, the description discloses significant behavioral details: the stateless predicted-vs-observed check, the 'prediction_check' flag for 'clamped' speed, and the degraded response format on incompatible builds or missing slices. This adds substantial transparency about return values and edge cases.

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 concise and well-structured: it starts with the primary purpose, then details the return data fields, and ends with degradation behavior. Each sentence adds value, with no redundancy or irrelevant content.

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 fully enumerates the return types (per-role time/filament, speed/flow ranges, global distributions, per-layer aggregates, prediction_check) and explicitly mentions degradation scenarios. For a zero-parameter tool, this is complete and self-sufficient.

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 zero parameters, and the schema coverage is 100%, so there is nothing to add. The baseline for 0 params is 4, and the description compensates by clearly describing the output semantics, which is the relevant aspect here.

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 explicitly states the tool's function: 'Per-feature breakdown of the last slice + a stateless predicted-vs-observed flow check.' It answers 'which feature is the time hog' directly, clearly distinguishing this from sibling tools like get_slice_status or get_slice_warnings by focusing on per-feature time/flow breakdown.

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 explicit when-to-use guidance: 'Answers which feature is the time hog directly instead of trial slicing.' It also states when it cannot be used: 'Degrades to {"available": false, "reason": ...} on fork builds that don't emit the breakdown, or when there is no valid slice.' This gives clear context and exclusions.

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