uprof_collect

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

With no annotations, the description fully carries the behavioral disclosure burden. It reveals that pid attach requires duration_sec, that timeout can kill the collection (default 300s), that non-zero app_exit_code is surfaced as a warning so crashes aren't mistaken for clean profiles, and that in mock mode the target runs but profile numbers are synthetic. This is rich, useful behavioral detail.

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, well-organized paragraph with the main purpose front-loaded. Every sentence adds value, parameter names are neatly backticked, and it avoids redundancy while covering many details. It is appropriately sized for a 10-parameter tool and wastes no words.

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 the tool's complexity (10 parameters, no annotations), the description is remarkably complete. It covers nearly all parameters, explains pitfalls (attach requires duration, only 'tbp' on non-AMD), describes timeout behavior and warning semantics, and tells the agent how to use the result (feed to report/compare tools). The existence of an output schema means return values need not be detailed, making this description 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?

Schema description coverage is 0%, so the description must compensate. It does: it explains command, pid, config (including non-AMD restriction and allow_unknown), call_graph, extra_events, label, timeout_sec, duration_sec, and allow_unknown, adding meaning far beyond raw schema. Only working_dir is omitted, but 9/10 parameters are enriched with defaults, constraints, and examples, which is outstanding.

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 opens with 'Run a uProf collection and store the result; returns a `result_id` handle.' This states a specific verb ('Run') and resource ('uProf collection'), and clearly distinguishes from sibling report/compare tools by producing a result_id for them to consume. It unambiguously answers what the tool does.

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 gives strong usage context: 'Pass exactly one target: command... or pid', mentions uprof_check for listing configs, and says to feed result_id to report/compare tools. However, it does not explicitly state when NOT to use this tool or name alternative tools ('use uprof_list_results instead'), so it falls short of the most explicit standard.

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