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

Annotations declare it is a non-read-only, non-idempotent, open-world write, and the description adds the key behavioral fact those annotations don't convey: the operation is asynchronous and must be polled via get_report until completed/failed. It does not explain the idempotencyKey's retry behavior, but that detail is already in the schema.

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?

Two short sentences with the deprecation warning and its replacement front-loaded, followed by the essential async workflow. Every clause carries weight; nothing is redundant.

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 two-parameter tool with no output schema, it covers purpose, deprecation, and the polling loop needed to get a result. The one small gap is that it doesn't say what the queued scan returns (an id or handle) to poll with, though get_report is named.

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 projectId and idempotencyKey are fully documented in the schema. The description only restates 'by id' and adds no format or constraint detail beyond it, so the baseline of 3 applies.

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 ('Queues a scan of a project by id') and immediately distinguishes itself from the sibling that supersedes it ('Deprecated: use scan_site'). An agent can tell exactly what this does and why it might not want it.

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?

Explicitly names the preferred alternative (scan_site) and gives the downstream workflow step ('Poll get_report until status is completed or failed'), which defines when the job is finished. Nothing about selection or follow-through is left to inference.

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