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

Annotations already declare readOnlyHint, idempotentHint and non-destructive, so safety is covered. The description adds genuinely non-obvious behavior beyond them: this is a long-poll that blocks up to 50 seconds by default. It stops short of saying what happens on timeout (pending result? error?), which matters for a blocking call.

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 no filler, and the blocking behavior is front-loaded after the purpose. Slightly terse for a polling tool but efficient rather than padded.

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?

Output schema exists so return values needn't be described, and annotations cover safety. What's still missing is the timeout outcome and re-poll strategy, which an agent needs to use a 50-second blocking endpoint correctly.

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 0%, so the description must carry parameter meaning; it partially does by revealing the default wait of 50 seconds, which the schema does not state. However, wait_seconds=0 semantics (presumably non-blocking poll) and the job_id 'job_' format/where to obtain it are never explained.

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 ('Check a job ... get its files when it's done'), which is unambiguous. No sibling tool polls job status, so differentiation isn't needed, but the description never mentions where job ids come from or what a 'job' is in this PDF-centric toolset.

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?

'Check a job that was still running' implies the usage context (you already have a job id from a prior async call), but there is no explicit when-to-use/when-not, nor guidance on re-polling versus blocking. Usage is only inferable.

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