chrome_fill

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

No annotations are provided, so the description carries the full burden. It discloses that the tool uses click/select/delete/type input, which suggests it may simulate user interaction, but it does not disclose behavior like whether it clears existing value, whether it waits for elements, or whether it handles contenteditable differently. It also mentions 'Chrome' in the description, implying it requires Chrome. However, the 'click/select/delete/type' sequence is a useful behavioral hint beyond the schema, but it lacks details on side effects such as focus changes or potential for overwriting.

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 sentence that is concise and front-loaded with the core purpose. It doesn't waste words, but it could be more structured by adding a second sentence for usage guidance. Given the tool's complexity (12 parameters), a slightly longer description would be warranted, but as is, it's efficient.

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 high complexity (12 parameters, no output schema, no annotations), the description is insufficient. It doesn't explain how to target the element (which parameters to use), what happens with the submit flag, or how background vs foreground affects behavior. An agent would struggle to know which parameters are required for which scenarios. The description leaves too much to inference. It should at least hint at usage patterns.

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 42%, meaning many parameters lack descriptions. The description itself adds no parameter-specific semantics; it doesn't mention 'uid', 'selector', 'targetId', 'domFallback', 'maxElements', etc. However, some parameters have schema descriptions (submit, targetId, background, urlIncludes, titleIncludes). With 42% coverage, the description should compensate for the undocumented parameters, but it does not. Thus, it's below baseline 3 for compensation, but given the baseline of 3 for high coverage is not met, this is a gap. Score 3 is generous because the schema covers some key ones.

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 states a specific verb ('set') and resource ('text input, textarea, or contenteditable'), and mentions the mechanism ('using Chrome click/select/delete/type input'), which implies a multi-step interaction. This is somewhat clear but could be more precise about what 'full value' means in context and how it differs from chrome_type (which might append or type incrementally). The siblings include chrome_type, chrome_click, and chrome_find, so the description helps distinguish from chrome_type but not as explicitly as it could.

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 does not provide any guidance on when to use this tool versus its siblings. For example, it doesn't say 'use this to replace the entire input value, whereas chrome_type appends text.' Given the presence of chrome_type and chrome_click, explicit distinction would be helpful for an agent deciding between these tools. The description only states what it does, not when to prefer it over alternatives.

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