Reindex Website Source and Wait

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

The description discloses the full lifecycle: job enqueueing, polling until completed/failed, the done:false/note budget-exhaustion case, the auth modes, the specific 401/403/404/504 errors, and the fact that a timeout may still leave the job running server-side. Even with idempotentHint=true and readOnlyHint=false present, this text adds meaningful behavior beyond 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 dense but every sentence carries information: purpose, return value, prerequisites, auth requirements, error semantics, and related tools. Information is front-loaded with the tool's core behavior before the polling details. No filler or tautology.

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 tool with no output schema, the description compensates by specifying the returned fields, the partial-result note, timeout behavior, and error cases. Combined with the 100%-covered input schema, an agent has everything needed to invoke this tool correctly and handle its edge cases.

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%, so the schema already documents appId, urlId, and timeoutMs well. The description adds context about why timeoutMs defaults to 45s and that appId is required in B2B mode, but it mostly reinforces schema-level meaning rather than introducing new parameter semantics. A baseline 3 is appropriate.

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 pair ('re-crawl and re-embed'), names the exact resource (a previously crawled URL), and immediately distinguishes the wait behavior from the non-wait sibling by explaining it enqueues then polls. The return shape is stated, so an agent can tell this tool apart from ethora-sources-site-reindex-v2 and ethora-sources-site-crawl-v2-wait without inspecting schemas.

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?

The description clearly states prerequisites: the URL must already be indexed from ethora-sources-site-list-v2 and crawled with ethora-sources-site-crawl-v2. It explains when the wait matters (polls until completed/failed, budget-exhaustion note) and gives related tool references, though it does not explicitly say 'use the non-wait variant if you do not need to block'.

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