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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds useful context that inputs are untrusted and that authorization (merchant_authorized) is required for clone/asset purposes, but it says nothing about idempotency behavior, the wait/cursor polling model, or what dry_run does.

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?

A single front-loaded sentence with no filler, which is good, but for a 12-parameter mutation with a polling model it is under-specified rather than genuinely concise. Nothing is wasted, but too little earns a place.

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 a complex 12-param write tool with zero schema description coverage and no output schema, the description is far too thin. An agent cannot determine from it how to sequence the call, what idempotency_key semantics are, or how cursor/wait_seconds interact.

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 0% across 12 parameters, seven of them required, so the description carries the full explanatory burden. It only gestures at max_awt ('AWT cap'), merchant_authorized ('rights'), and two purpose enum values ('clone/assets') — leaving url, build_id, workspace, idempotency_key, cursor, wait_seconds, target_path, page_type_hint, and dry_run completely undocumented.

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 verb/resource pair 'Capture ... reference evidence' is identifiable, but 'AWT cap' and 'untrusted reference evidence' are unexplained jargon. It gives no signal distinguishing it from the sibling references_compare, and never mentions that the unit being ingested is a URL into a build.

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?

There is no explicit when-to-use statement, no prerequisites beyond a cryptic 'clone/assets require rights', and no routing to siblings such as references_compare or research_search. The agent must infer call conditions entirely.

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