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

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=true, and destructiveHint=false, and the description is fully consistent with them (scraping is a non-destructive, repeatable read of an external resource). The description adds useful context on supported sources and extracted fields, but discloses no failure modes — an agent gets no warning that postings may be expired, login-walled, or blocked by bot protection, which is significant for a scraper that hits third-party sites. No annotation contradiction.

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?

A single sentence that front-loads the action verb and compacts the output fields and supported sources efficiently. Every element earns its place; there is no filler, no repetition of the title, and no redundant restating of schema content.

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?

An output schema exists, both parameters are fully documented, and annotations cover read-only/idempotent/non-destructive safety, so the description need not restate return values or safety. It covers what is extracted and from which sources. The main remaining gap is failure-mode transparency for a network-touching scraper (expired postings, restricted pages, rate limits), which is the one thing that could surprise an agent during real use.

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% (url: 'The URL of the job posting'; api_key: 'Optional API key override'), so the baseline is 3. The description adds meaning beyond the schema by enumerating acceptable URL sources (LinkedIn, Greenhouse, Lever, Ashby, Wuzzuf), helping an agent judge whether a given URL is a valid input. It adds nothing for api_key, but the schema already describes it fully.

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 description uses a specific verb ('scrape and extract'), names the resource ('job description from a job URL'), enumerates the extraction targets (job description, company name, requirements, responsibilities), and lists supported platforms (LinkedIn, Greenhouse, Lever, Ashby, Wuzzuf). This clearly distinguishes it from siblings like civify_parse_cv, civify_score_ats, and civify_tailor_cv, which operate on CVs rather than job posting URLs.

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?

Usage context is implied: when an agent has a job posting URL from one of the listed platforms, this tool scrapes it. However, the description never explicitly states when-not-to-use it or names alternatives among the 16 siblings; the appropriate-use signal must be inferred from the URL source list rather than stated directly.

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