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

With no annotations supplied, the description must carry the full behavioral burden, but it only says it is a "prompt kit with step-by-step instructions." It never clarifies whether the tool executes a polish operation or merely returns prompt assets, what input it expects, whether it is read-only, what output form results, or what the "30-day support" means operationally — an ambiguity that could mislead about the tool's actual behavior.

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, none of which lead with what the tool does; the functional fragment is buried behind a generic "AI-powered ... intelligence pack" opener and closes with a commercial promise. Most of the text is filler that an agent cannot 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 single-parameter tool with no annotations and no output schema, the description should at minimum define the operation, expected input, and result shape — it defines none of these. It is a product blurb rather than a functional specification.

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% for the single optional "query" parameter, so the schema already conveys its meaning; the description adds nothing about how a query scopes the polish. Baseline 3 applies when the schema does the work and the description neither helps nor harms.

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 only functional phrasing is "complaint polish tool workflow," which simply restates the tool name without explaining what polishing a complaint entails (rewriting tone? fixing typos? localizing?). The remainder is marketing copy ("AI-powered restaurant & brand intelligence pack", "30-day support promise") that adds no resource or action detail, and nothing distinguishes it from siblings like complaint-rewrite-tool, complaint-audit-tool, or complaint-reply-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?

There is no statement of when to use this tool, when not to, or which sibling to pick instead, despite ~10 closely named alternates (complaint-write/rewrite/audit/sort/summary/tpl-tool and the parallel *-polish-tool family). The description offers only promotional assurances ("no prompt engineering needed"), not selection guidance.

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