browser_snapshot

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

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It states 'Read' (non-destructive), 'bounded' (with a max_items parameter), and 'accessibility-tree projection' (structured output, not screenshot). However, it doesn't describe what happens if the collaboration_id is invalid, whether the operation is expensive, if there are rate limits, or if the tool modifies any state. The description provides basic safety context but lacks depth for a tool with no other metadata.

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, short sentence that front-loads the key action and subject. Every word contributes meaning: 'Read' (non-destructive), 'bounded' (size-limited), 'accessibility-tree projection' (structured output), 'explicitly shared tab' (scope). There is no wasted text, but the sentence could be slightly more readable by breaking or adding context. It earns a 4 for being efficient yet clear enough.

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 the tool has 2 parameters, no output schema, and no annotations, the description is incomplete for safe and effective use. It doesn't describe the return format, error conditions, prerequisites (e.g., needing a valid collaboration_id from a prior tool), or how this projection differs from a full accessibility tree. The browser_tabs sibling likely provides tab IDs, but the link is missing. A tool reading shared tab state needs more context about lifecycle and dependencies.

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%, meaning the JSON schema has no textual descriptions for parameters. The description adds meaning: 'collaboration_id' is identified as identifying 'one explicitly shared tab', and 'max_items' is contextualized as a 'bounded' constraint on the projection. However, it doesn't explain what max_items unit is (items=nodes?), what a reasonable value range implies, or how collaboration_id is obtained. The baseline for 0% coverage is low, and the description partially compensates but leaves gaps.

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 specific verbs ('Read') and nouns ('accessibility-tree projection', 'shared tab'), clearly indicating the tool reads a structured accessibility view from a specific context. However, it doesn't distinguish this tool from siblings like browser_diagnostics, browser_screenshot, or browser_schedule_snapshot, which could also relate to capturing information from a tab. The term 'bounded' and 'explicitly shared' adds clarity, but the exact scope (vs other read tools) is ambiguous.

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 context is provided about when to use this tool versus alternatives such as browser_screenshot (visual capture), browser_status (general status), or browser_schedule_snapshot (scheduled counterpart). There is no indication of prerequisites (e.g., must call browser_open first, or collaboration_id must be valid) or when not to use it. The agent making a choice among many sibling tools is left with minimal decision guidance.

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