screenshot

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

With no annotations, the description carries the full behavioral burden and does substantial work: return format (inline PNG vs. temp-file path fallback on SDKs without image content), a hard security constraint (blocked after a secret fill), and the coordinate unit contract tying one image pixel to one CSS pixel for `@ (x,y)` and `click_at`. It does not say whether the capture is viewport-only or full-page, which is the main remaining behavioral gap.

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?

Four short sentences, each carrying distinct information: what it does, what it returns, the fallback, the blocking constraint, and the coordinate semantics. The primary capability is front-loaded and nothing is repeated from structured fields.

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 zero params, no annotations and no output schema, the description covers return shape, fallback path, a security exclusion and coordinate units — enough for correct invocation. The one omission is capture scope (viewport vs. full page) and any size/perf caveat, which an agent may need when deciding between this and `snapshot`.

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 tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline is 4. The description instead clarifies the implicit output contract, which is the useful thing to add here.

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 and resource ('Capture a screenshot of the current page') and immediately clarifies the output form. It also distinguishes itself from the sibling `snapshot` by explaining that the image lets a multimodal model disambiguate by the same element indices, so the agent can tell the two apart without opening either tool.

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?

Clearly gives the conditions under which this is the right call (multimodal model needs to see the page) and states an explicit exclusion mechanism ('Wraith blocks this tool after a secret fill'). It stops short of naming a direct alternative such as 'use snapshot for element indices only', so the when-not guidance is environmental rather than comparative.

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