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

The annotations already declare non-read-only, open-world, idempotent, non-destructive, so the safety profile is covered. The description adds genuinely new context: 'Counts toward the workspace's Refix usage' discloses a quota cost, and it warns against starting a duplicate investigation to poll progress. It stops short of describing latency or what happens to an existing session when reused, keeping it below a 5.

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?

Front-loaded with the three modes and the exclusivity rule before the workflow caveats; every clause carries operational content. It is dense and reads as a runbook rather than a crisp definition, which keeps it out of the top band.

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?

Five parameters, all documented, an output schema exists so return values need no explanation, and the description still covers the two things an agent would plausibly get wrong: passing multiple selectors at once and re-investigating to poll for results. Nothing needed to invoke it correctly 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 100% and each parameter has a description, so the baseline is 3. The description adds a constraint the schema does not encode – the mutual exclusivity of session_id, response_to_input_id and finding_id – plus the guidance that session_id preserves context for follow-ups, which is real value beyond 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 description names the specific verb and resource ('Start a new Refix investigation') and enumerates the three call modes: new question, clarification answer via response_to_input_id, and finding drill-down via finding_id. It explicitly names the sibling tools it depends on (refix_list_findings, refix_get_investigation, refix_get_context), so an agent can place it in the workflow without opening schemas.

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 explicit routing rules: 'Send at most one of session_id, response_to_input_id or finding_id', use session_id for follow-ups in the same chat, and 'call refix_get_investigation for the result; do not start another investigation to check progress'. It also prescribes the fallback path when a named tool is not in usable_sources – tell the user it is not connected and ask before starting.

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