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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description goes well beyond them: exact failure modes and status codes (501 hosted_scraping_not_enabled, 403 for unclaimed sandbox workspaces), the robots.txt/https-only constraint, and the required credential scope. That is precisely the kind of operational context annotations cannot carry.

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 with the action and the partial-update rule before the prerequisite laundry list, and no sentence is filler. The auth/flag/workspace prerequisites arrive as a dense run of clauses, which is efficient but slightly list-like rather than structured.

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 an 11-parameter mutation tool with no output schema, it covers the failure surface, auth scope, workspace state and safety constraints thoroughly. The remaining gap is that it says nothing about what a successful update returns or how to verify the change (e.g. list_scrape_jobs).

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%, so the baseline is 3; the description earns above that by adding two constraints absent from the schema: a minProperties-style 'at least one field' rule and the clearing semantics of 'Set plan_selector to null to clear it' (the schema only shows string|null with minLength 1, which does not imply null clears). Other parameters are left to 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?

Opens with a specific verb+resource ('Change a scrape job') and immediately pins down the partial-update contract ('send job_id and only the fields you want to change, at least one'), which distinguishes it from create_scrape_job, delete_scrape_job and run_scrape_job. It never names those siblings explicitly, so the differentiation is implied rather than stated.

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 clear invocation guidance ('send job_id and only the fields you want to change, at least one') plus three hard preconditions: the hosted-scraping release flag, a commerce:configure credential, and a claimed workspace. It stops short of naming alternatives, so an agent must infer that run_scrape_job triggers execution and create_scrape_job builds a new job.

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