Get Screen Diff

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

With no annotations, the description carries the full burden and does so well: it discloses the return shape (diagnostics, no image), the baseline caching side effect, the read-only default (updateBaseline=false), and the first-observation baseline rule. It lacks detail on the distance scale/threshold semantics an agent would need to act on the number.

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?

Three tight sentences, front-loaded with the core action and immediately followed by the output nature, usage rationale, and default. No wasted words.

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 3-param, read-only compute tool with no output schema, the description explains the return nature and baseline behavior adequately. It stops just short of interpreting what the returned distance value means for decision-making.

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 cacheKey, displayId, and updateBaseline are already well documented in the schema (including the default-false meaning). The description only restates the default value, adding little beyond the schema.

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?

States a specific verb (compute the perceptual-hash distance) and resource (current screen vs cached baseline), and distinguishes itself from siblings by noting it 'Returns only diagnostics — no image' and shares state with screenshot_if_changed. An agent can tell it apart from screenshot/wait_for_change without opening schemas.

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?

Gives a clear context — 'Useful for polling whether a screen has changed before spending vision tokens' — and notes the read-only default. It does not explicitly exclude or route to alternatives like wait_for_change, so it stops short of full when/when-not guidance.

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