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

Far exceeds the read-only/idempotent annotations: it enumerates every status value, explains partial-delivery behavior ('a job that stopped part way keeps what it delivered'), discloses credit semantics ('charged as words are delivered, never above the tier asked for'), and gives throughput expectations. Nothing about runtime behavior is left implicit.

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?

Dense but front-loaded: it leads with scope, then status semantics, then result shape, then polling advice. Every sentence carries information, though the single-block paragraph could be broken up for faster scanning.

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 carries the full burden of describing return values and does so: status enum, sections done of total, words written, credit cap and charges, and what 'result' holds on success. An agent has everything needed to interpret a response.

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% and the single parameter is fully documented in the schema as 'job.id returned by generate_content, polish or humanize.' The description restates the same origin-tool information without adding format, validation, or lookup detail 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?

Names a specific verb and resource ('Check a background job') and immediately scopes which jobs it covers: long drafts from generate_content (>4,000 words) or polish/humanize (>3,000 words). This distinguishes it cleanly from get_generation and list_generations, which handle finished/finished-draft artifacts.

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?

Gives explicit routing: use get_generation to read the actual draft once a job succeeds. It also tells the agent how often to call it ('poll every 30-60 seconds rather than in a tight loop') and why, which is exactly the operative guidance for a polling tool.

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