Crawl Website Source and Wait

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

Annotations provide only high-level hints (readOnly=false, not destructive, not idempotent). The description adds crucial behavioral detail: it enqueues then polls, returns a structured result, and discloses that a timeout does not guarantee the job is cancelled—it may still complete. It also explains auth requirements and error codes (401/403, 400, 504), which are not in the annotations.

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 compact yet dense, leading with the primary action, then the return shape, prerequisites, auth, and errors. Every sentence earns its place—there is no filler. It is front-loaded with the core behavior and uses a structured paragraph style that aids scanning.

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?

With no output schema, the description fully explains the return object, including the edge case of `done:false`. It covers prerequisites, auth modes, error handling, and the timeout behavior. It also references a sibling tool for follow-up, making it complete for an agent to decide and call 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?

Schema coverage is 100%, so baseline is 3, but the description adds meaningful context beyond the schema: it explains why `timeoutMs` defaults to 45000 (to stay under typical client limits), warns that `followLink` can ingest many pages, and clarifies when `appId` is required versus ignored. This enriches each parameter's meaning.

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 opens with a specific verb and resource ('Crawl a website URL') and clarifies the distinctive wait-for-completion behavior, which separates it from the likely non-waiting sibling `ethora-sources-site-crawl-v2`. It also states the outcome and what the return value contains, leaving no ambiguity about the tool's job.

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 states prerequisites (selected app or explicit `appId`), which auth modes are accepted, and what to do on timeout (check with `ethora-sources-site-list-v2`). It also explains the partial-failure case (`done: false` with a `note`) and notes that the job usually finishes server-side, giving clear guidance on when to use this tool versus waiting/checking elsewhere.

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