run_task

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

With no annotations, the description carries the full burden and does so: it warns that control is handed off to an autonomous AI, describes the return value (completion summary with success status and action log), explains the multi-agent contract (FSB-issued agent_id captured server-side), states the concurrency cap and its default/range, and enumerates specific failure codes (AGENT_CAP_REACHED, TAB_NOT_OWNED, TAB_INCORNITO_NOT_SUPPORTED, TAB_OUT_OF_SCOPE). This is unusually rich behavioral disclosure.

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?

Front-loads the critical gating rule and the alternative routing before the contract details, which is the right ordering. It is dense and long, but every clause (cap, ownership errors, return shape) is decision-relevant rather than padding, so it stops short of a 5 only on sheer volume.

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?

No output schema exists, and the description compensates by describing the return (completion summary, success status, action log). Combined with the auth model, concurrency limits, and error taxonomy, an agent has everything needed to decide whether to call it and to interpret a rejection.

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 coverage is 100%, so the schema already fully documents `task` as a natural-language description. The description's parameter-adjacent content (agent_id, cap) concerns invocation/environment rather than the `task` argument itself, so this sits at the baseline for a fully-covered 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 action and scope: it hands control to FSB's built-in AI which autonomously decides the steps. It explicitly separates itself from the large set of manual browser siblings (navigate, click, type_text, execute_js, etc.), so an agent can route correctly without inspecting 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 an explicit gating condition ('Only use this tool if the user explicitly requests autopilot, asks to "run a task", or says "let FSB handle it"') and names the alternative for every other case, plus the rationale (manual tools are more reliable and give full control). Nothing is left to inference.

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