spidra_crawl_extract

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

Beyond the readOnlyHint and destructiveHint annotations, the description adds key context: no pages are re-crawled, only AI token credits are charged, a new jobId is returned immediately, and the source crawl must be completed. This gives the agent a clear model of the tool's behavior and cost implications.

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 description is three focused sentences with no filler. The main action is front-loaded, followed by cost-saving rationale and immediately actionable usage details (polling, precondition). Every sentence contributes value.

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 simple two-parameter job-creation tool, the description covers the use case, cost, return behavior, polling workflow, and a required precondition. With good annotations and full schema coverage, no significant information is missing for an agent to decide and invoke correctly.

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?

The input schema already provides 100% coverage with descriptions for both jobId and transformInstruction. The description does not add additional parameter-specific details, so it meets the baseline for schema-covered parameters but does not enhance understanding of parameter formats or constraints.

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 clearly states the tool runs a new extraction prompt over an already-completed crawl without re-crawling pages. It distinguishes itself from crawling tools by emphasizing the reuse of completed crawls, and from status tools by being an action that returns a jobId.

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?

It explicitly conditions usage on the source crawl being 'completed' and positions it as a cheaper alternative to crawling again. It also directs the caller to poll spidra_check_crawl_status with the returned jobId, though it does not name alternative tools for other scenarios.

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