update_reference

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

With no annotations provided, the description carries the full behavioral disclosure burden. It does well by explaining side effects: the old reference is backed up, a fresh capture may be taken, and a first baseline can be created for pages lacking a reference. It does not mention profile/auth requirements, return behavior, or failure cases, so it is not fully exhaustive, but the core mutation behavior and safety mechanism are transparent.

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 dense but front-loaded with the primary purpose, and every clause adds information: fallback order, baseline creation, backup behavior, and confirmation requirement. It is somewhat run-on and could be split into clearer sentences, but there is no fluff or redundancy.

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 mutating tool with no annotations and no output schema, the description covers the essential operational context: what the tool does, how the source is resolved, that the old reference is preserved, and when confirmation is required. The main gap is the unexplained profile parameter, which may matter in an auth-aware environment, but the core decision-making information is present.

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%, so the description must compensate for the schema's silence. It adds real meaning for source (explicitly an image) and confirm (must be true after user confirmation), and page is implied. However, the profile parameter is never explained, leaving one of four parameters semantically 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 description uses a specific verb and resource: "Make the current look of a page its reference screenshot." It goes beyond a generic statement by specifying the fallback chain (source image → latest qa_page capture → fresh capture), which clearly distinguishes it from sibling tools like capture or qa_page. An agent can immediately understand what this tool changes and when it is invoked.

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 gives a clear usage condition: "Only do this when the USER has confirmed the look is intended; set confirm=true." This tells the agent when it is appropriate to invoke the tool and how to express that precondition through the confirm parameter. It does not explicitly name alternative sibling tools or state when NOT to use it, but the context and fallback logic strongly imply its specialized role.

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