Profile cook cost

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds behavioral context about the sampling methodology (N samples × intervalMs) and output composition (hotspots, warnings), which goes beyond the annotations without contradicting them.

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?

Two sentences, front-loaded with the key action ('Read-only') and purpose. Includes a compact return signature. No redundant or placeholder content; every sentence earns its place.

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 output schema present and annotations covering safety, the description still adds purpose, use case, and return structure. It is sufficient for an agent to understand when and how to invoke the tool, and the inclusion of the alternative tool makes the context 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% with each parameter already described in detail. The description reinforces the relationship between samples and intervalMs (window) and mentions targetFps forwarding, but does not add significant new meaning beyond what the schema provides. Baseline 3 applies.

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 samples cook times over a window and ranks hotspot nodes by p95 cook time. It uses specific verbs ('sample', 'rank') and identifies the resource (cook times, hotspot nodes). It also distinguishes itself from get_td_performance by targeting intermittent stalls a single snapshot misses.

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 this tool: 'Use this to diagnose intermittent stalls that a single get_td_performance snapshot misses.' It names the alternative tool and the specific scenario where this tool is superior, providing clear guidance for agent selection.

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