research_next

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

Annotations declare destructiveHint=true and readOnlyHint=false, yet the description reads like a benign navigation helper ('start or continue', 'next step') and never warns that this call can irreversibly stop screening or abandon undecided articles — exactly what the `confirm` parameter enables. The omitted destructive profile is the single most important thing an agent needs here, and 'idempotent' is also unaddressed.

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?

It is short and front-loads the workflow role, which is good. However, roughly a third of the text is spent on `do` and `ask_researcher`, parameters that are absent from the schema, so the brevity comes at the cost of accuracy rather than being earned.

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?

An output schema exists, so return values need not be explained. But for a destructive, non-read-only workflow driver with a `confirm` gate, the description omits the confirmation semantics, the run-selection behavior, and the guide() prerequisite detail — the gaps are exactly where an agent would go wrong.

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 100%, so a baseline of 3 would apply — but the description actively misleads by describing a `do` parameter ('naming the tools to call') and an `ask_researcher=true` flag that do not exist in the schema. It adds nothing about the three real parameters (run_id, confirm, project), and the invented ones could cause a malformed call.

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 calls it 'the next step from the question to the report,' which signals a workflow-driving tool, but it never says concretely what the step does. Against a sibling list containing next_report, next_synthesis, next_triage_batch, next_screening_batch and bot_next, this is too generic to distinguish itself — an agent cannot tell why it would pick research_next over those.

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?

'Start or continue a review' hints at the entry condition, and 'Rules: guide("research")' implies a prerequisite call to guide, but that is left as an unexplained fragment with no syntax or consequence. No explicit when-to-use/when-not, and no comparison against the many sibling `next_*` tools that presumably advance other phases.

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