get_paused_info

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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the description is fully consistent with them. Beyond that it discloses non-obvious behavioral traits: returned frameIndex values and callFrameIds are valid only for the current pause and expire after any step or resume, which is exactly the kind of statefulness an agent cannot infer from annotations or schema.

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?

Three sentences, front-loaded with what the tool returns, then the negative boundary, then the expiry caveat and next step. No sentence restates the name or repeats schema content verbatim.

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?

Output schema exists, so return shape needn't be explained; annotations cover the safety profile; schema covers all parameters. What remains for the description — pause state dependency, ephemeral handles, and the escape hatch to evaluate_script — is all present.

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 100%, so all three parameters are documented in structured fields and the baseline is 3. The description adds real value by tying frameIndex to the pause lifecycle (expires on step/resume) and by pointing at evaluate_script as the consumer of that index; includeScopes and maxScopeDepth are left to the schema.

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?

States a specific verb (inspects) plus three concrete resources (call stack, source locations, call-frame scopes) and the precondition that execution is already paused. It also explicitly negates the two adjacent capabilities (creating a pause, resuming), which separates it from pause_or_resume and step without the agent needing to inspect schemas.

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?

Gives the trigger condition (after a code/XHR breakpoint or explicit pause), the two things it does not do, and a concrete follow-on path: use evaluate_script with frameIndex for an expression, then step or pause_or_resume(action="resume"). Alternatives are named explicitly rather than implied.

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