session_annotate

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

The description reveals important behavioral traits not visible from the name or annotations: the annotation persists for hold_ms and a screenshot is captured. It also mentions the option of a frame and tone. Since no annotations are provided, this carries the full burden, and it does well in disclosing side effects like screenshot capture.

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 sentences, no fluff, with the primary action front-loaded and supporting details following. Every clause adds useful information about function or behavior.

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 the tool's core behavior and parameters, but there is no output schema and no mention of what the tool returns. The phrase 'captured as a screenshot' hints at an artifact but doesn't clearly state whether the result is a screenshot reference or something else. For an agent deciding whether to call this tool announced, the return value remains ambiguous.

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 description explicitly explains message, target, tone, and hold_ms: 'callout with your message', 'frame around a target element', 'tone info, success or failure', and directly references hold_ms. It does not mention session_id, but that is self-evident from the context. It compensates well for the 0% schema description coverage.

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 'Draw' and resource 'recorded video', then elaborates with callout, message, optional frame, tone, hold_ms, and screenshot capture. This clearly distinguishes it from sibling tools like session_screenshot or session_act, which do different things. The scope is 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?

No explicit guidance on when to use this tool versus alternatives. It does not say 'use this for annotating video' or compare with session_screenshot for plain captures. The context of 'recorded video' implies its domain, but there is no direct statement about when to choose it over other session tools.

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