spidra_retry_crawl_page

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

Adds substantive behavior beyond the annotations: it does not hit the network (consistent with openWorldHint=false), the page's stored data is replaced (a real side effect the write-hint annotations only imply), and the cost is limited to that page's AI credits. The transformInstruction/schema precondition is disclosed nowhere else.

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?

Four short sentences, front-loaded with the action and its key side effect, then the when-to-use, the id source, the precondition, and the cost. Nothing is padding.

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 two-parameter tool with no output schema, it covers action, side effect, precondition, cost and id provenance. The return value is only described as 'the new data', leaving the shape of the re-extracted result unstated, which is the one remaining gap.

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 100% and both required parameters are documented in the schema itself. The description only repeats provenance for pageId (from spidra_crawl_pages), matching the schema's own wording, and adds no format or validation detail for jobId.

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?

States a specific verb and resource: re-run a crawl's extraction on a single saved page and return new data. The scope words 'one saved page' and 'doesn't visit the site' distinguish it from spidra_crawl_extract and spidra_retry_batch without needing their schemas opened.

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 the triggering condition explicitly ('when one or two pages came back empty or wrong'), a prerequisite ('only crawls with a transformInstruction or schema can be retried'), and routes the agent to spidra_crawl_pages to obtain the id. The 'one or two' framing implicitly steers bulk repair elsewhere.

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