observation.bundle

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds some behavioral context beyond annotations by mentioning 'before/after context' and 'consistent semantic views,' but it does not explain what 'object evidence' means or what the captured output contains.

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 a single, front-loaded sentence with no filler. It conveys the core action and key qualifiers efficiently, though the phrase 'semantic views' and 'object evidence' are somewhat abstract and could be clearer.

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?

With no output schema, the description should explain what the tool returns, but it does not. It also omits important behavioral details around the six parameters, the meaning of 'before/after context,' and how this bundle differs from a simple viewport capture. The presence of read-only and idempotent annotations helps, but the missing output and parameter semantics leave notable gaps.

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 0%, so the description carries the burden of explaining parameters. It adds partial meaning: 'one to three' maps to the views array constraints and 'object evidence' hints at object_name, but it provides no guidance on max_size, overlays, viewport_id, or display_mode, which remain unexplained.

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 ('Capture') and names a defined resource ('one to three consistent semantic views') along with meaningful qualifiers ('before/after context and object evidence'). It gives a clear idea of what the tool produces, though it does not explicitly name sibling tools to differentiate itself.

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 offers no guidance on when to use this tool versus siblings like viewport.capture, context.snapshot, or object.inspect. There are no stated conditions, exclusions, or references to alternative tools, leaving the agent to infer when observation.bundle is preferred.

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