Report a batch, get the next

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

Annotations only declare openWorldHint and destructiveHint; the description goes well beyond them by documenting per-action semantics (navigate opens url, run_js needs page-script execution and returns raw JSON, click is a real click), the results array shape, error payload fields, and strong invariants ('Never invent outcomes or execute a batch twice'). Its one gap is that it never calls out the destructive side effects the destructiveHint annotation implies.

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 purpose is front-loaded, but the rest is a dense run-on block of semicolon-clause jargon and abbreviations with no grouping or bullets. Every sentence carries information, yet the structure forces the reader to parse hard to extract the rules.

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?

With no output schema, the description correctly shoulders the burden of describing returns: 'done:{status,counts,files}', the {actionId,result:<raw MCP result>} envelope, and the error shape with completed/error/results. Combined with the resume and review guidance, an agent has enough to drive the loop, though the batching/counting protocol could be spelled out a bit more.

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% across 5 params, so the description must carry the load, and it does: batch is a numbered batch that gets echoed, results holds one entry per run_js/tool in action order (none for navigate/click), error carries a message, completed counts fully finished actions, and runId drives resume with no results. This is substantive meaning beyond the bare types in the 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?

The opening sentence names a specific verb+resource ('Records a numbered batch and returns the next actions or done:{status,counts,files}'), which is precise and unambiguous. It's clear this is the work-loop primitive, but the description never explicitly contrasts itself with sibling host_start, so the differentiation is implicit rather than stated.

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 guidance: 'Report problem rows with run_report; resolve review only after checking the destination,' and 'Resume an interrupted host run with host_next(runId) and no results.' That tells the agent both when to use this tool and when to hand off to run_report. It lacks an explicit when-not-to-use statement, keeping it from a 5.

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