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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful traits beyond that: 'unbilled' (cost behavior) and 'never starts another extraction' (no side effects). The trailing 'discovery reports blueprint maintenance' is opaque jargon that adds confusion rather than clarity.

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?

The core action and the no-extraction guarantee are front-loaded and earn their place. The final clause ('Allowlisted, unbilled scraping preview; discovery reports blueprint maintenance') is dense internal jargon that an external agent cannot decode, which dilutes an otherwise brief statement.

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 does helpfully distinguish two return states (pending metadata vs. an authorized completed result page). But with three parameters at 0% schema coverage and a multi-step job workflow implied by siblings, an agent still lacks enough to call this correctly on the first try.

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% across three parameters (job_id, cursor, page_size), so the description is the only place meaning could be added — and it says nothing about any of them. The phrase 'result page' loosely hints at pagination but never explains cursor or page_size semantics, so it fails to compensate for the coverage gap.

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?

The opening sentence gives a specific verb (read) and resource (pending metadata / a completed result page), so the agent knows this fetches job output rather than triggering work. The 'Never starts another extraction' clause reinforces scope. However, it does not differentiate itself from the sibling get_job, leaving ambiguity about which retrieval tool to pick.

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?

'Never starts another extraction' functions as a when-not hint, implying this is a read-only polling/retrieval path. But there is no explicit guidance on when to use get_results versus get_job or discover, and no prerequisites (e.g., that a submit_job must have run first) are stated. Usage is only implied.

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