uprof_timechart

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

With no annotations provided, the description carries the full burden. It discloses key behaviors: sampling at a configurable interval (minimum 10), returning summaries (min/max/mean/last) rather than the full series, and the fact that CSV files remain in result_dir. It also clarifies mock mode vs real hardware. This goes well beyond a simple tautology, though it could mention side effects like file writing more explicitly.

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 compact yet information-dense. It front-loads the primary action, uses backticks for parameter names, and conveys all key points in a few sentences without redundancy. Every sentence earns its place by adding crucial context (events list, intervals, summaries, hardware requirement).

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?

Despite the absence of annotations and schema descriptions, the description covers the essential context: what the tool does, parameters, return format (summaries), the location of raw data (result_dir), and environment requirements (AMD hardware vs mock). An output schema exists, so the description does not need to detail return values, but it still explains the semantics. It is complete 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 coverage is 0%, so the description must compensate—and it does thoroughly. It explains that `events` are timechart categories and lists them, states the minimum for `interval_ms` (10), specifies `duration_sec` as the sampling window, and explains `command` as an optional command to run during sampling. Every parameter receives meaningful semantic context beyond the raw schema types.

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 function: 'Sample system power/frequency/thermal counters over time and summarize them.' This is a specific verb+resource (sample/timechart categories) and the scope is distinct from sibling tools like uprof_report_raw or uprof_list_results, which focus on reporting or listing results rather than sampling and summarizing.

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?

The description provides clear usage context: it is for sampling counters over a time interval and getting summary statistics. It also notes the option to run a command and the hardware prerequisite ('Real data needs AMD hardware'). However, it does not explicitly name alternative tools for when the full series is needed or when other reporting tools are more appropriate, so it lacks explicit exclusions.

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