walkthrough

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

With no annotations, the description carries the full behavioral burden and delivers: arg-dispatch side effects (single-step explain vs highlight-only vs narrated tour vs clear vs navigation), the teleprompter UX dependency on the highlights[] pattern, and the TTS quirk where numbered lists are read as 'one dot… two dot'. It also discloses formatting constraints (real newlines not literal backslash-n, avoid ## headers, use **bold**) and coupling to global voice/bubble/autoplay settings — all beyond what structured fields could express.

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?

Long, but every sentence earns its place — the density reflects six behavioral modes plus critical formatting rules. Front-loaded with purpose, triggers, and the exclusion before diving into dispatch details; the sectioned guidance (multi-point steps, TTS no-numbered-lists, markdown rules) is compact and directly actionable with zero filler.

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 tool this complex — three params, six action modes, a nested highlights structure, no output schema, no annotations — nothing needed for correct invocation is missing: entry conditions, exclusions, formatting rules, settings coupling, and status-on-no-args are all present. The only minor gap, explicit return-format details beyond the no-args status, is low-risk since the tool's effects are primarily visual/audible UI state.

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% with unusually detailed per-property descriptions, so baseline is 3. The description adds meaning by synthesizing parameters into a behavior matrix (one step with explanation = explain; one without = highlight; multiple = tour) and by prescribing usage patterns ('keep explanation to 1–2 intro sentences… put each point in its own highlights[] entry'). It supplements `step` with 'pass step index for goto' and maps the full action enum to behaviors, though the schema already documents individual properties.

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?

Opens with a specific verb+resource+scope ('Show, explain, and tour code in VS Code') and frames itself as the one tool for code presentation with commentary. Explicitly names its sibling as the alternative for commentary-free jumps: 'Do NOT use for jumping to code without commentary — use show_code instead.' An agent can distinguish it from show_code without opening the 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?

Lists concrete trigger phrases ('explain code, walk through code, tour a codebase, ask how does this work, navigate an active tour, clear bubbles, or check walkthrough state') so an agent knows exactly when to fire it. Provides an explicit exclusion and names the sibling alternative (show_code). The dispatch matrix further tells the agent which argument shape to choose per intent.

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