get_page_html

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

With no annotations provided, the description carries full burden. It discloses important behavioral traits: it annotates interactive elements and removes scripts/styles. However, it doesn't mention whether this is a read-only operation, potential performance impact, authentication requirements, or what format the annotations take. The description adds value but leaves gaps.

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, efficient sentence that front-loads the core purpose ('Get the HTML') and immediately adds qualifying details. Every phrase adds value: specifying the source ('web page in the active playback window'), key features ('interactive elements annotated'), and exclusions ('Scripts and styles are removed'). Zero wasted words.

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?

For a tool with no annotations, no output schema, and moderate complexity (HTML extraction with annotations), the description is adequate but incomplete. It covers what the tool does and key transformations, but doesn't describe the return format, error conditions, or how annotations are represented. Given the lack of structured fields, more behavioral context would be helpful.

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 mentions no parameters directly, but the single parameter (tab_id) has 100% schema description coverage that clearly explains its purpose and usage. With zero parameters described in the tool description itself, and high schema coverage, the baseline is appropriately met without needing compensation.

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 the specific action ('Get the HTML'), target resource ('web page in the active playback window'), and key characteristics ('with interactive elements annotated', 'Scripts and styles are removed'). It distinguishes itself from sibling tools like get_screenshot (visual capture) and get_search_html (likely filtered HTML).

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 implies usage for retrieving annotated HTML from a playback context, but provides no explicit guidance on when to use this tool versus alternatives like get_screenshot or get_search_html. There's no mention of prerequisites, performance considerations, or specific scenarios where this tool is preferred.

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