snap_report_async_start

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the trailing 'Read-only' adds no new information. What the description does contribute beyond the annotations is genuinely behavioral: the call is asynchronous and returns a report_run_id that must be polled via snap_report_async_status before download, which shapes how an agent must sequence calls. It stops short of noting whether concurrent runs are limited or how long results persist.

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 short sentences, all front-loaded: capability and differentiator first, return value and follow-up workflow second, safety last. Nothing is padded and the async lifecycle is conveyed in minimal space.

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?

The async lifecycle and sibling routing are well covered for a job-starting tool, and there is no output schema, so the return-value note (report_run_id) is appropriately placed in the description. However, a 6-parameter tool at 0% schema coverage with 4 required fields leaves the agent guessing at formats and the breakdown/granularity semantics, which is a material completeness gap.

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 6 parameters (entity, id, start_time, end_time, breakdown, granularity), and the description says nothing about any of them — no acceptable time formats, no meaning of the entity/breakdown interplay, no note that granularity defaults to DAY. With zero schema documentation, the description carried the full burden for parameter meaning and delivered none of it.

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 ('Start a large CSV report') and immediately distinguishes it from the synchronous path with the parenthetical 'no size limit, unlike the synchronous reports'. An agent can tell this apart from snap_report and from the status/download siblings without opening a schema.

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?

The description gives an explicit selection rule ('large ... no size limit, unlike the synchronous reports') and spells out the follow-up chain: poll with snap_report_async_status, then retrieve with snap_report_async_download. Both the condition for choosing this tool and the downstream sequence are named rather than left to inference.

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