Request human handoff

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

Annotations already declare readOnlyHint=false and openWorldHint=false, so the mutation/session-bound nature is covered structurally. The description adds the useful nuance that it only marks state in the existing session rather than performing the handoff itself, but says nothing about what happens next (session pause, timeout, or required follow-up call).

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?

A single front-loaded sentence with no filler; the scoping phrase 'in the existing browser session' earns its place by ruling out new-session behavior.

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 one-parameter state-change tool with annotations covering safety and no output schema, this is close to adequate. However, in a sibling set that includes captcha_wait and captcha_resume, the description leaves the post-handoff lifecycle (does the agent wait, resume, or stop?) unspecified.

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?

Only one parameter and schema description coverage is 100%, so the schema fully documents session_id. The description adds no syntax, format, or sourcing detail beyond what the schema provides, which is the expected baseline.

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 (mark) and a specific resource (the current challenge) with the resulting state (awaiting a person). An agent can tell it apart from captcha_inspect/analyze, though it never explicitly contrasts itself with the other captcha siblings.

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 phrase 'awaiting a person' hints at the scenario, but there is no explicit when-to-use, when-not-to-use, or relationship to siblings like captcha_wait or captcha_resume. An agent must infer when handoff is preferable to waiting or resuming.

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