measure_predictability

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

Annotations include readOnlyHint and openWorldHint, but the description goes further by explicitly warning that the text is sent to the SignsOfAI server, mentions the configurable endpoint, and clarifies interpretive limitations. This adds substantial behavioral context beyond the annotations.

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 three sentences, each with a distinct purpose: definition, interpretation caveat, and network warning. It is front-loaded and free of fluff, making every sentence earn its place.

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?

The description covers the core purpose, caveats, and network behavior, which addresses most usage concerns. However, with no output schema, it would be more complete if it explicitly stated the return format (e.g., a numeric perplexity score). This minor gap prevents a perfect score.

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 input schema has 100% parameter description coverage for text, model, and language, so the description adds no new parameter-level semantics. The baseline of 3 applies because the schema already documents the parameters sufficiently.

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 identifies the tool's function: measuring perplexity/predictability of phrasing. The verb 'measures' and the resource (language model's predictability) are specific, and the mention of 'unlike the offline tools' helps distinguish it from sibling tools.

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 provides important usage context: it is a signal, not proof, and it highlights that this tool sends text to a remote server unlike offline tools. However, it does not explicitly state when to prefer this tool over alternatives like check_originality or analyze_ai_writing.

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