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

With no annotations, the description carries the full burden and does so thoroughly: quota (none consumed), rate limits (1000/IP/UTC day, 429 READ_RATE_LIMITED with Retry-After), 30-day expiry, and the security model (checkId is a bearer capability enabling share links). It also decodes status and failureCode values.

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?

Substantially longer than typical, but the length is justified by the polling semantics, status vocabulary, and limits it must convey. It is well organized into purpose, polling, status decoding, and constraints, with the key behavior first.

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?

There is no output schema and no annotations, so the description must explain the return shape and error surface. It enumerates status values, summary fields, per-engine fields (cited vs mentioned), failureCode reasons, and the no_answer non-failure case, leaving nothing critical unstated.

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% and documents the 22-character format, so the baseline is 3. The description adds meaning the schema lacks: checkId is random and whoever holds it can read the test, which tells the agent it is a shareable secret rather than an opaque identifier.

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 ('Read an AI citation test') and immediately ties it to the creation call it complements, so it is unmistakable next to create_citation_check. The polling nature of the read is front-loaded.

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 explicit operational guidance: call again every 3 seconds while pending/running, stop when done or failed. It also describes the lifecycle relative to the POST that starts the test. It stops short of naming the sibling create_citation_check tool, but the workflow condition is otherwise unambiguous.

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