browser_read

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It clearly discloses limitations: url/title are page-level, ref/CSS support text/html/value, semantic role/text/label support text only with optional name/exact. This gives the agent a concrete model of the tool's behavior. It also states that unsupported combinations should use snapshot/ref or CSS, setting expectations. This is strong transparency for a read tool, so 5.

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 well-structured with labels (Purpose, Constraints, Example) and is concise—each section adds useful information. The example is helpful. However, there is a truncation ellipsis ('…') that suggests some content may be missing, which slightly reduces clarity. Otherwise it's efficient, so 4.

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's moderate complexity (6 parameters, 5 enum values) and the presence of an output schema, the description covers the main facets: what data can be read, the valid target types, and the constraints on combinations. It lacks a full explanation of the target and session parameters, and the fallback instruction is somewhat ambiguous. With the output schema covering return values, this is well-rounded but has a few gaps, so 4.

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 coverage is 0%, so the description must compensate. It explains the meaning of the 'what' parameter by listing the supported values, and it clarifies how 'target_type' interacts with these values (e.g., role/text/label only support text). It also mentions the 'name' and 'exact' parameters as optional for semantic roles. However, it does not explicitly explain the 'target' and 'session' parameters; the example shows session usage, but target is left implicit. Still, this is a substantial addition beyond the bare schema, so 4.

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 opens with a clear purpose statement—'Read data from the page'—and enumerates the specific data types (text, HTML, value, URL/title). This directly distinguishes it from sibling browser tools like browser_act or browser_eval, so it earns a 5.

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?

It provides clear context for when to use this tool (to read data from the page) and includes constraints on which target types support which data types. It also suggests using snapshot/ref or CSS for unsupported combinations, offering a fallback. However, it does not explicitly name alternative sibling tools or give definitive when-not-to-use criteria, so it's a 4 rather than a 5.

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