screenshot_session

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

Without annotations, the description fully discloses behavior: it prepares captures by neutralizing sticky headers, disabling animations, emulating reduced motion, forcing scroll-reveal sections visible, and reports these in capture_prep. It also explains the raw parameter for unprepared stitches. This is comprehensive and 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 concise with no redundancy. It front-loads the purpose, then explains options, behavior, and usage guidance in a logical flow. Every sentence adds distinct value.

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?

The description covers purpose, usage, behavior, and parameter semantics adequately for a 4-parameter tool with no output schema. It mentions return value (image path) but does not detail error conditions or prerequisites beyond an implicit active session. Still, it is largely complete.

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 coverage is 100% and parameters are already well-described. The description adds minor but useful context, e.g., 'for citing evidence' for selector and clarifying raw's effect on full-page captures. This justifies a baseline 3 plus incremental value.

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 screenshots the session's current page as-is, with 'no actions performed.' It distinguishes from interactive tools that already return screenshots, and specifies full-page vs viewport capture. The verb and resource are specific and unambiguous.

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 explicitly says 'use to grab state at a point in a workflow' and warns 'don't call this after every step' because interactive tools already return screenshots. This provides clear when-to-use and when-not-to-use guidance, effectively distinguishing it from sibling tools.

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