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

Annotations declare readOnlyHint=true and destructiveHint=false, so the description correctly does not repeat these. It adds behavioral context by stating what the tool returns (0-100 score, band, single most severe flag) and that the full breakdown is a paid $29 report, which is a limitation. The disclaimer that it is 'not a claim about authorship' clarifies what the tool does not do.

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 moderately concise, starting with the primary purpose and patterns, then output, then limitation, then disclaimer. It is front-loaded and each sentence adds value, though it could be slightly tighter. It is well-structured for an agent to parse quickly.

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 the simple single-parameter input and no output schema, the description explains the return values (score, band, flag) and the paid tier, which is important for agent expectations. It also clarifies the non-authorship claim. There is no mention of rate limits or error conditions, but for a read-only analysis tool with one parameter, this is largely complete.

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 schema provides 100% coverage for the single 'text' parameter with description 'The manuscript or excerpt text to analyze (longer excerpts score more reliably)'. The tool description adds no additional parameter semantics beyond reiterating that it analyzes manuscript text. Baseline 3 is appropriate since schema covers the parameter fully.

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 tool's function: 'Analyze manuscript text for patterns associated with AI-generated prose' and enumerates specific patterns (cliche-phrase density, uniform sentence rhythm, repeated paragraph openers, overused transition words). It also specifies the output (score, band, most severe flag) and disambiguates from the sibling 'slopcheck' (YouTube channel risk) by focusing on manuscripts. The disclaimer 'Not a claim about authorship' further clarifies scope.

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 description implies usage for writers self-editing before publication ('a writer can use to self-edit before publishing'). It does not explicitly name alternatives or exclusions, but the context of manuscript analysis is clear, and no sibling tool directly competes. The paid full-breakdown note also sets expectations about the free vs. paid tiers.

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