bridge_submit

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

Annotations already signal readOnlyHint=false, openWorldHint=true, and destructiveHint=true, so the safety profile is available. The description adds useful behavioral context beyond those annotations: asynchronous execution, whole UTF-8 prompt and text-artifact handling, a stable requestId, and a durable receipt. It does not elaborate on destructive side effects, but the annotation covers that signal without contradiction.

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 short and front-loaded, with the primary action stated first. Every phrase adds some information, but the telegraphic fragments ('Choose provider. Whole UTF-8 prompt...') make it read less smoothly than a well-structured sentence while still remaining efficient.

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 10 parameters, a destructiveHint annotation, and no output schema, the description is under-specified. It explains the async submission pattern but omits critical call context such as how project relates to bridge_projects, the meaning of onBusy and delivery, the distinction between prompt and promptFile, and the behavior of acceptDesktopPolicy. An agent has enough to invoke it at a basic level but not enough to use it correctly across realistic scenarios.

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 must compensate for explaining parameters. It only vaguely maps 'Choose provider' to provider, 'whole UTF-8 prompt and text artifacts' to prompt/artifacts, and 'stable requestId' to requestId. Six other parameters (project, onBusy, delivery, threadId, promptFile, acceptDesktopPolicy) receive no semantic explanation in either the description or schema, leaving a significant gap.

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 clearly identifies the operation: starting or continuing a Codex or Claude Code CLI session asynchronously. It also distinguishes its role from the sibling receipt tool by instructing 'Poll bridge_receipt.' It is specific enough that an agent can understand the tool's core function without inspecting the schema, though it does not explicitly contrast with steering or cancellation 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 only usage guidance is 'Poll bridge_receipt,' which implies the expected follow-up pattern after submission. However, there is no explicit statement about when to use bridge_submit versus alternatives like bridge_steer or bridge_session_manage, nor any mention of conditions such as onBusy or delivery. Usage context is implied rather than fully specified.

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