submit_claude_task

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

Goes well beyond the annotations (which only say it is not read-only, not idempotent, not destructive): no shell/local-file/MCP/messaging/publishing capability, subscription auth checked before every task, model pinned to Sonnet, single shared active task, 20-minute timeout, no API fallback, and a warning not to infer allowance from token counts. This is exactly the operational context an agent needs before invoking.

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?

Dense and front-loaded, with the capability boundary and constraints stated early and no filler. The telegraphic sentence fragments ('No shell, local-file, MCP, messaging or publishing tools.') cost a little readability but each clause carries distinct information.

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 covers the operational essentials: async execution, timeout, polling, auth, one-task concurrency, and the no-fallback limitation. It does not say what the submission returns (e.g., a task identifier to use with get_claude_task), which is the one remaining gap.

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 0%, so the description carries the burden and does explain both parameters: task is a text-analysis payload (with the test string as an example) and allow_web enables optional public web research. It omits the task 1–50,000 character limits and the allow_web=false default, which remain schema-only.

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 ('Delegate') and resource ('a user-authorized text-analysis task') plus the execution channel ('official Claude Code subscription login', 'Uses Sonnet'). The Claude/Codex split is self-evident against sibling submit_codex_task, so an agent can pick the right submit tool without opening either schema.

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 concrete usage conditions: allow_web=true for public web research, polling required after submission, one shared active task at a time, and a prescribed first test ('Reply exactly CLAUDE_BRIDGE_TEST_OK'). It stops short of explicitly naming get_claude_task as the polling companion, leaving that inference to the agent.

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