workload_fetch

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

Annotations already declare idempotentHint=true, openWorldHint=true, and destructiveHint=false, so the description's job is mostly to add context. It does: network fetch from GitHub, SHA-256 integrity verification against a pinned hash, and a specific cache path in ~/Library/Caches/metal-gpu-trace. It omits what happens on checksum mismatch or offline failure, which keeps it from a 5.

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?

Three sentences, front-loaded with the action and integrity check, followed by cache location and reuse semantics. The provenance sentence about the workloads workflow justifies trust in the binary rather than padding, and no sentence is redundant.

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 rich annotations and an output schema present, the description covers the essential mechanics: source, verification, cache location, and idempotent reuse. The remaining gap is failure behavior (checksum mismatch, no network), which matters for an open-world download but is a modest omission.

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 100% and the single `name` parameter is documented in the schema with an example and a pointer to workload_list. The description itself adds no parameter guidance, so the baseline of 3 is appropriate given the schema carries the load.

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 names a specific action and resource: downloading a test program from the project's GitHub releases, verifying its SHA-256, and caching it locally. An agent can distinguish this from read-only siblings like workload_list or perf_run because the caching and download behavior is stated. It stops short of explicitly directing agents to workload_list for valid names, which would sharpen differentiation.

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?

'later calls reuse it' implies the tool is safely re-invoked and that a first call seeds the cache, which is useful implied guidance. However, there is no explicit when-to-use instruction (e.g. 'call before perf_run if the workload is not cached') and no stated alternatives or exclusions relative to workload_list or presentmon_install.

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