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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description goes well past that: it names what is destroyed (the job plus its run history), declares irreversibility, explains the pause workaround, and documents two concrete failure modes with their status codes (501 and 403) plus the required credential and scope (commerce:configure).

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?

Front-loaded correctly: the destructive action and its irreversibility come first, then the alternative, then gating and prerequisites. Each sentence is doing work except 'Runs honour robots.txt and fetch only public https pages,' which concerns run-time fetching behavior rather than deletion and is tangential to this tool's invocation.

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 single-parameter destructive mutation with no output schema, the description covers everything material: what is removed, irreversibility, the safer alternative, availability gating, auth scope, and workspace-claim precondition. An agent has no open questions that would cause a wrong call.

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 job_id description already tells the agent it is the 'id on a list_scrape_jobs result,' so the parameter is fully documented in structured data. The description adds nothing further about the ID's format or origin, which is acceptable given the schema carries it, but it earns no credit above baseline.

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?

Opens with a specific verb and resource and extends the scope beyond the object itself: 'Delete a scrape job and its run history.' That scope detail is the key fact an agent needs to distinguish this from a mere status change, and it immediately names the sibling it is not (update_scrape_job with enabled false).

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?

Explicitly states the when-not ('This cannot be undone') and names the alternative and the condition that selects it ('update_scrape_job with enabled false pauses it instead'). It also gives preconditions that decide whether the call is even viable: release flag gating (501 hosted_scraping_not_enabled) and workspace claim status (403 for sandbox keys).

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