humanizer-polish

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

Beyond the annotations, the description discloses important behaviors: default mode strips Markdown markers like ## and **, normalizes line endings to LF, and does not touch lexical content. The Markdown-stripping warning is material for safe use. This is not an annotation contradiction because the destructive warning concerns transformed content, not an external side effect.

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 compact and front-loads the core purpose before the exclusions, with no filler. It loses one point for being a dense single run-on sentence with many semicolon-separated clauses, which is slightly harder to scan than a short structured list.

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 rich input schema, output schema, annotations, and the explicit usage exclusions, an agent has enough information to select and invoke the tool correctly. The only minor gap is that the lexical/sense-editing exclusion does not point to which sibling tool should be used instead.

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%, and the input schema already documents the mode enum and text scope in rich detail. The top-level description adds some behavioral context but repeats much of what the schema already explains, so it stays at the baseline for fully documented schemas.

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 opens with the specific operation 'типографическая нормализация' and enumerates concrete targets: dashes, quotes, ellipsis, invisible characters, markup markers, and LF line endings. This clearly identifies what the tool does, but it does not explicitly name or contrast sibling tools, so it stops short of full sibling differentiation.

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 has an explicit 'Когда не использовать' section. It warns not to run on Markdown/markup with the default mode, names the correct modes to use instead (--preserve-markup and --typographic), and states that the tool does not perform lexical or semantic editing. This provides strong when/when-not/alternative guidance.

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