Dispatch a read-only Harness review

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

With annotations present the bar is disclosure beyond structure, and this description delivers: it warns that scope fields are 'task instructions, not enforced per-path filesystem isolation,' that read content may be sent to an external model provider even though Relay uses loopback, that the calling agent MUST read assistantText before claiming completion, and that still-running reviews must not be treated as finished. These are non-obvious operational facts an agent could not get from readOnlyHint/openWorldHint alone.

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 first sentence front-loads the purpose well, but the body is long and partly redundant with the input schema (the same path-reference paragraph is repeated verbatim in three schema fields). Sentences such as the authorization re-prompting note are load-bearing but buried mid-paragraph, diluting scannability.

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 high-complexity, 17-parameter tool with no output schema, the description covers the full lifecycle an agent must handle: required inputs, what the scope fields mean, data-egress implications, the post-start wait_run loop, the terminal states, and the assistantText verification step. Nothing essential for correct invocation and follow-through is missing.

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 71%, and the description adds genuine meaning for the critical required fields (provider/model/authorizationBasis exist so the named-model request is machine-identifiable and the approval can identify the processing destination), which the schema only partially conveys. Several parameters (sessionId, agentPreset, sessionMode, reasoningEffort, idempotencyKey) remain undocumented in both description and schema, so it does not fully close the 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 opening sentence states a specific verb and resource with scope: 'Create or reuse a native Harness session with the permission preset fixed to read-only.' Combined with the review-focused parameters (reviewTargets, contextReadScope) the agent can tell this apart from start_run/start_deployment, though the description never explicitly contrasts itself with those 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?

It gives real routing and workflow guidance: required provider/model/authorizationBasis, the instruction not to re-ask the user for authorization, and an explicit post-start sequence ('share webUrl and keep wait_run until succeeded/failed/cancelled/needs_attention'). It also covers the review-then-fix case. It stops short of naming alternatives like start_run or validate_task_scope as the thing to use instead when the task is not a review.

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