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

Even though annotations mark readOnlyHint=false and destructiveHint=false, the description goes well beyond that by disclosing the review lifecycle, the returned handle/claim_token, the need for a human to open save_url to persist it, and the 30-day auto-deletion unless saved. This is substantial behavioral context that annotations alone do not provide.

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 five sentences with no filler: it front-loads the purpose, then the returned handle, then the persistence flow. Every sentence contributes necessary information, and the formatting with backticked identifiers and explicit return values keeps it scannable.

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 no output schema, the description carries the full burden of explaining return values, and it does: review slug, claim_token, review_url, and save_url. It also connects to sibling tools (add_screenshot/add_note, save_url's human step) and explains the auto-deletion policy. This is complete for a create tool of this complexity.

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 the schema already documents title, summary, and product_url clearly. The description adds general context about creating a review but does not meaningfully elaborate on parameter semantics beyond what the schema provides, so the baseline score of 3 is appropriate.

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 uses a specific verb ('Start a new... review') and names the precise resource (Cobalt Capture review). It clearly explains the tool's role as the entry point for compiling browser-testing or QA findings into a shareable report, which distinguishes it from sibling tools like add_screenshot and add_note.

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?

The description provides clear context for when to use the tool: starting a new review from a testing/QA run. It also implicitly routes to add_screenshot/add_note by stating the returned claim_token must be passed to those tools for appending content. It stops short of explicitly listing when-not-to-use cases or alternatives like update_review, so it earns a 4 rather than a 5.

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