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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower; however the description adds little beyond them. It doesn't explain what statuses exist besides pending, whether terminal states are reported, or what the wait parameter does behaviorally.

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, front-loaded with the purpose. No filler, though the second sentence is terse to the point of ambiguity.

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 polling tool with no output schema, the description should at minimum imply the response shape and the full set of returnable states. It gives only fragmentary status vocabulary and leaves the wait behavior unexplained.

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 the baseline is 3; but the description never mentions the 'wait' parameter, which is the one semantic that actually needs explanation ('Wait briefly' is vague on duration and blocking semantics). It adds no meaning 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?

States a specific verb (read) and resource (generation status), distinguishing it from report_start_generation which initiates the job. It is clear enough to identify the tool, though it doesn't name the sibling it complements.

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?

No explicit when-to-use guidance beyond the implicit pairing with report_start_generation. The line 'Queued and running are pending' gives a status vocabulary hint but not conditions for calling, polling cadence, or when to stop.

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