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

Annotations already declare this a safe read (readOnly, non-destructive, closed-world). The description adds context annotations don't cover: it returns as soon as any state changes or after roughly 50 seconds, and it lists the state vocabulary (pending, rendering, saved, failed) plus what is returned once saved. That is real behavioral value beyond the annotations.

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 sentences, with the return content and the poll timeout front-loaded and no filler. Minor awkwardness ('A render link's files:' fragment) but efficient overall.

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?

With no output schema, the description usefully covers the return shape (states, file name, size when saved) and the polling behavior. However, it omits render_id semantics and any failure/error or retry guidance, so an agent is not fully equipped for edge cases.

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%, so the description must compensate. It does explain the semantics of the states parameter well ('pass back the states of the last answer'), but render_id is never described beyond the implicit link to a render link, leaving half the parameters undocumented.

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?

It clearly describes the resource (a render link's files and their per-drawing states) and the long-poll return behavior, so an agent knows what the call yields. It doesn't explicitly frame the verb as 'wait/poll' nor differentiate itself from the sibling wait_drawing, leaving the name to carry that distinction.

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?

'Pass back the states of the last answer' implies an iterative poll loop, which is useful usage guidance. But it never says when to choose this over status, wait_drawing, or render_link, and no exclusions or prerequisites are given.

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