humanizer_assess_text

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

With no annotations, the description carries the full burden and does reasonably well: it discloses the model backend dependency, the relative slowness versus lint_text, the exact return payload (six dimension scores, quoted issues, pattern-checker score), and that runs averages repeats to reduce noise. It omits auth/credential needs implied by the claude-cli and anthropic backends, and any failure or cost 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?

The purpose and output scale are front-loaded in the first sentence, followed by return shape, then per-argument notes - a sensible order with no filler. The 'Args:' block is slightly list-like but each line adds information the schema lacks.

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 three-parameter tool with no annotations and no output schema, the description covers purpose, scoring direction, latency tradeoff, return payload, and all three parameters. Missing only edge behavior such as what happens with empty or very long text and how backend credentials are supplied.

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 0%, so the description must compensate, and it does: text is the input to assess, backend enumerates the valid choices (auto, claude-cli, anthropic, mock), and runs is explained as repeat-and-average noise reduction rather than just a number. It does not state per-parameter defaults or how auto backend selection resolves, which are the remaining gaps.

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 gives a specific verb and resource - scoring how AI-written a text reads - plus the output scale (0-100, higher = more AI-like) and the mechanism (blind rubric). It also positions itself against the sibling humanizer_lint_text, so an agent can tell the two apart without opening either schema.

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?

It establishes context by noting the model backend makes it slower than lint_text, which implicitly routes latency-sensitive or cheap checks to lint_text. It stops short of an explicit when-to-use / when-not-to-use statement or a recommendation for when the deeper assessment is worth the cost.

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