Start a background crawl

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

With no annotations, the description carries the full burden, and it delivers: it discloses that the call returns immediately with a jobId, that pages are appended as JSON lines to outFile, that it is resumable, and that re-running skips already-present ids. This gives an agent a clear model of side effects and asynchronous behavior without needing extra context.

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?

Three dense sentences front-load the core purpose and immediate return behavior, then explain file semantics and defaults. No filler or wasted words; every sentence earns its place.

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 6-parameter tool with no output schema and no annotations, the description covers the essential flow: start, get jobId, poll status, write JSON lines, resume. It does not describe error behavior or the concurrency/delay tradeoffs, but those are secondary given the schema's parameter descriptions and the clear reference to the status sibling.

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 adds real value by explaining that bookId/startId/endId/outFile default to a specific dictionary (Lisan al-Arab, bookId 122, ids 1..9305) and that outFile has resumable append semantics. delayMs and concurrency are left to the schema, which already documents their defaults and bounds.

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 ('Starts crawling') and resource ('contiguous range of content ids from one islamweb library book'), and immediately distinguishes itself from siblings by noting it runs in the background and returns a jobId for polling via islamweb_crawl_status. This makes the tool's role unambiguous relative to the other crawl-related tools.

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?

Clear context is provided: call this to start a background crawl of an id range, and poll islamweb_crawl_status with the returned jobId. It also explains resumability and defaults, which helps decide when to use it. However, it does not explicitly say when not to use it or name alternatives like islamweb_fetch_entry for single-entry fetches.

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