collect_profile

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

The description adds useful context beyond the annotations by noting the collection is bounded and requires explicit authorization, which suggests safety constraints. The annotations already declare destructive/non-read-only behavior, so the extra detail is valuable and non-contradictory.

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 terse sentence that is front-loaded with the action and includes the key safety condition, with no redundant wording.

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?

For a complex tool with 13 parameters and zero schema descriptions, this one-sentence description is insufficient to guide correct usage, especially regarding parameter relationships, prerequisites, and the nature of the output. The presence of an output schema does not compensate for the lack of input guidance.

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 description does not explain any of the 13 input parameters, and the schema has 0% coverage, so the agent has no guidance on how to set pid, output_path, events, etc. The only hint is the mode list, which mirrors the enum and adds little meaning.

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 action (run collection), the specific tools (perf record/stat/sched/lock/off-CPU), and the bounded nature, distinguishing it from sibling collection tools like collect_project_workload and execute_collection_plan.

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 explicitly mentions that it should only be used after server and per-call authorization, providing a clear condition for invocation. However, it does not describe when not to use it or name alternative tools, so it stops short of a 5.

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