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

No annotations are supplied, so the description carries the full disclosure burden. It hints at the output shape (a prompt pack with examples) but says nothing about whether the call is read-only, whether it mutates state, what the caller needs to provide, or how the result differs from the gen/check/write siblings.

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?

Two short sentences with no filler, and the deliverable is stated up front. But the brevity comes from under-specification rather than economy: what remains is marketing framing, not information an agent can act on.

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 template/workflow tool with no annotations and no output schema, the description should at minimum say what the template governs and what the agent gets back. Instead it offers generic promotional language, leaving both the domain and the return contract undefined.

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?

There is a single optional "query" parameter with 100% schema description coverage, so the schema already explains it. The description adds no syntax, scoping, or example values beyond that, which makes the high-coverage baseline of 3 appropriate.

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?

"perf tpl tool system" restates the tool name rather than describing an action or artifact; the only concrete claim is that it delivers a "copy-paste prompt pack with examples." It never specifies what "perf" covers (performance review? performance marketing?) and does nothing to distinguish it from perf-gen-tool, perf-tpl-tool's own siblings like perf-audit-tool or perf-write-tool.

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 audience is named ("marketing and operations leaders") but there is no when-to-use condition, no prerequisite, and no routing to or away from the many sibling tools in the perf-* family. An agent has no basis for choosing this over perf-gen-tool or perf-write-tool.

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