frame_all

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

With no annotations, the description carries the full burden. It discloses NO_UNDO (irreversible), that it only adjusts the view (no screenshot side effects), and that responses go through server-side cap. These are useful behavioral traits beyond what the name implies.

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?

Two short sentences with key info front-loaded: the function call, NO_UNDO, view-only scope, and server cap. It's concise, though the technical snippet 'apply_response_cap' could be clearer to a general agent.

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 simple viewport operation, the description covers purpose, undo behavior, and non-screenshot scope. However, it omits any explanation of the ctx parameter and doesn't describe return values or potential side effects beyond NO_UNDO. Given one parameter and no output schema, this is a moderate gap.

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?

The schema has one required parameter 'ctx' with 0% description coverage, and the description doesn't explain ctx at all. Since schema coverage is zero and no parameter info is given, the description fails to compensate, leaving the parameter meaning 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 description clearly states it adjusts the view via viewport.frameAll() and explicitly notes it does **not** take a screenshot, which distinguishes it from capture tools. However, it doesn't explicitly say 'frame all objects' in plain language or contrast with frame_selection, so it's clear but not perfectly differentiated.

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 the context that this tool only adjusts the view and doesn't screenshot, implying when it should be used. But it doesn't mention alternatives like frame_selection for framing specific objects, so guidance on when to use vs alternatives is only implied.

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