presentmon_install

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

Goes well beyond annotations: names the network source (GitHub release), discloses SHA-256 verification against a pinned hash, gives the on-disk location (%LOCALAPPDATA%\metal-gpu-trace), and states the privilege requirement (admin or Performance Log Users group). This is exactly the auth/network/artifact context annotations cannot convey, and it is consistent with readOnlyHint=false/openWorldHint=true.

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?

Front-loads the platform constraint and packs platform, source, verification, destination, reuse semantics, and privileges into three dense sentences with no filler. Slightly long and run-on in the first sentence, but every clause carries distinct information.

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 parameters, rich annotations, and an output schema to carry return values, the description supplies everything else an agent needs: OS constraint, network dependency, integrity check, install path, idempotency, and privilege prerequisite.

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?

Zero parameters, so the baseline of 4 applies; there is nothing for the description to disambiguate.

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?

Specific verb+resource: downloads Intel's PresentMon console app from its GitHub release and installs it locally. The 'Windows only' qualifier and repeated references to perf_record/perf_attach make it clearly distinguishable from every sibling, which are all consumers rather than installers.

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 the tool is what perf_record and perf_attach depend on and that later calls reuse the installed copy, so an agent knows to install before recording. It lacks an explicit 'skip this if already installed / use X instead' clause, but idempotentHint and 'later calls reuse it' cover the main decision.

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