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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description usefully adds that this is an asynchronous queue operation returning a run ID and that access is paid and owner-only, but says nothing about idempotency behavior or run lifecycle beyond the ID — though the schema covers the idempotency key.

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?

Three compact clauses, front-loaded with the core action and return value, followed by cost/auth constraints. The final 'Access: keyless: subscription_required with a subscribe link' is slightly awkward but not wasteful.

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 create/queue tool with no output schema, the description supplies the return value (run ID), auth requirements, and scope limits, which is close to sufficient. The main omission is what the caller should do next to retrieve results, presumably via research_run_read.

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 100% and the configuration object is documented in detail in the schema itself, so the baseline applies. The description contributes no additional meaning to 'kind', 'request_id' or 'configuration' beyond calling the calculation 'bounded'.

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?

States a specific verb and resource ('Queue one bounded research calculation') plus the immediate result ('returns a queued run ID'), which is enough to distinguish it from research_run_list/read/cancel. It does not explicitly contrast itself with the dedicated task tools (fx_backtest_task, macro_heatmap_task), so it stops short of a 5.

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 clear gating context: paid, owner-only, subscription required with a subscribe link, and explicitly excludes live orders and model inference. It does not say what to do after submitting (e.g. poll with research_run_read), so the guidance is contextual but incomplete.

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