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

Annotations already carry openWorldHint=true and destructiveHint=true; the description reinforces both with concrete specifics: it 'Writes' the three vdd/clone-* artifacts, 'makes network requests to the target site', and explains the caching behavior where refresh=true 'bypasses a cached dataset and re-crawls'. This adds real behavioral context beyond the boolean hints and does not contradict them.

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 long but every sentence carries load: purpose, artifacts, parameter guidance, open-world side effect, and sibling routing. The technical detail on WordPress-aware inference and the Next.js + Payload + Postgres scaffold is relevant to what the tool produces, not padding. The core purpose is front-loaded in the first sentence.

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 an open-world destructive tool with no output schema, the description covers the essentials: what is written, cache/refresh semantics, network side effects, and when to use it. The remaining gap is the schema/description mismatch — 10 VDD-pipeline-style parameters (taskId, researchFindings, artifactFiles, etc.) are exposed for a tool explicitly outside that pipeline, and the tuning knobs mentioned in prose are absent from the schema, creating some invocation ambiguity.

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 baseline is 3; the description adds value by resolving the vague 'Freeform description input' schema text into actionable guidance ('Pass the domain as description'). However, the prose names tuning parameters (maxPages, timeoutMs, concurrency, crawl, browser, refresh) that do not exist anywhere in the input schema, leaving ambiguity about how an agent is supposed to supply them.

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 a specific verb+resource pair ('Crawl and capture a target domain into a clone dataset + manifest') and enumerates concrete output artifacts (vdd/clone-dataset.json, vdd/clone-manifest.json, vdd/clone.md). It also explicitly distinguishes itself from the 15 VDD siblings by stating it is 'not part of the VDD phase pipeline', so an agent can disambiguate it 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?

Gives an explicit use case ('Use for cloning an external site'), an explicit exclusion ('it is not part of the VDD phase pipeline'), and routes the agent to the alternative ('for the normal init→validate flow call those phase tools instead'), which maps directly to sibling tools like vdd_init and vdd_validate. It also flags the cost implication ('Open-world: makes network requests') so the agent can weigh side effects before invoking.

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