Step-by-Step Guide

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

Annotations already declare destructiveHint=true and non-read-only, so the bar is lower; the description nonetheless discloses what the artifacts are and, importantly, the exclusion property 'Never includes typed text', a privacy trait an agent cannot infer from the schema. It still doesn't say that an existing guide in outputDir is replaced, though the overwrite parameter partly covers that.

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?

One dense sentence plus a short qualifier, with the core transform front-loaded and no filler. The trailing 'Never includes typed text' is terse to the point of being slightly ambiguous about where the exclusion applies (captions, screenshots, or both).

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?

With seven fully described parameters, an output schema and annotations covering the write/destructive profile, the description supplies the missing conceptual picture of the output bundle. What remains thin is the prerequisite context (a recording must exist and carry markers) and any steering among the many sibling post-processing tools.

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 coverage is 100%, so the schema already documents ocr, input, title, format, outputDir, overwrite and sessionId, which sets the baseline at 3. The description corroborates the format enum ('Markdown and/or one HTML file') and hints at how markers shape the output, but adds no syntax or defaulting detail beyond the schema.

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 states a precise transform: an event log becomes a numbered how-to with per-step ringed screenshots, captions and marker headings, emitted as Markdown and/or a single HTML file. That verb+resource+output triple separates it cleanly from siblings like chapters, review_recording, convert and concat.

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?

Usage is only implied: you run it on a recording's event log to get a written guide. No sibling is named as an alternative or exclusion, so an agent deciding between step_guide, chapters and review_recording gets no routing help. The 'Never includes typed text' note hints at a privacy-sensitive situation but does not frame when to pick this tool.

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