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

Annotations only say readOnlyHint=false and destructiveHint=false, so the description must convey the mutation semantics — and it does: a NEW form is created, the source is untouched, and fidelity varies by source (exact copy for own forms, fields only for another account's live form). It also discloses the failure behavior (nothing is created when the URL isn't a form), which is valuable behavioral context beyond the annotations. It doesn't mention permissions, quota/credit consumption, or whether the clone can be undone.

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?

Front-loaded with the action and result, then the supported sources, then the usage trigger, then the failure mode — a logical progression with no filler sentences. The em-dash-heavy middle sentence is long but each clause adds a distinct source type. Slightly dense, but nothing is redundant.

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 mutation tool with no output schema, the description covers what gets created, what fidelity to expect per source, and what happens on a bad link. The main gap is the return side: it never indicates what the agent gets back on success (a form id or link?) or what 'it says so' looks like as a response, so the agent can't set expectations for post-clone follow-up.

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%, so url, title, and status are already documented with their defaults and enum. The description adds no parameter-level detail beyond the schema — it doesn't clarify how 'url exactly as the user gave it' is parsed or what 'fields only' means for which options survive. Baseline 3 applies when the schema does the heavy lifting.

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 and resource: 'Clone a form from its URL into a NEW form in the user's Xmagnet account — same fields, options and text.' It enumerates the supported source types (own forms, other-account live forms, Xmagnet landing pages, Google Forms, raw HTML), which implicitly separates it from create_form (blank creation) and clone_landing_page (page cloning). However, it never names a sibling tool directly, so the differentiation is inferred rather than stated.

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 gives an explicit trigger — 'Use when the user shares a form link and says clone / copy / duplicate / "make a form like this"' — which is the clearest when-to-use signal possible. It also covers the negative case (link is not a form → nothing created, tell the user plainly). What it lacks is routing guidance naming alternatives, such as when to use create_form instead of cloning.

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