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

Even though readOnlyHint and destructiveHint already cover safety, the description adds substantial behavioral context: blocking semantics, B2B auth requirements, specific 401/403/404 error cases, and the exact shape of success and timeout returns. This goes well 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 compact and front-loaded: purpose and blocking behavior first, then return shape, then auth and errors. Every sentence earns its place and there is no repetition of schema text.

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 explains the return contract (`done`, `state`, `job`, timeout case), terminal states, auth prerequisites, and error modes. The only minor omission, that the job continues after timeout, is reasonably inferable from 'read-only polling wrapper' and the timeout return shape.

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 baseline is 3. The description adds some useful semantic glue, such as timeoutMs being the wait cap and jobId coming from the create call, but it does not need to compensate for missing schema documentation.

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 precise verb ('Block until') and a specific resource ('users batch job') plus a clear terminal-state condition. It also explicitly identifies itself as a read-only polling wrapper around `ethora-users-batch-job-v2`, distinguishing it from one-shot status checks and from sibling wait 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?

The description clearly frames the use case: wait for a users batch job to finish after creation, and it warns that B2B auth must match the auth used to create the job. It does not explicitly name exclusions or alternatives like 'use ethora-users-batch-job-v2 for a single status check,' so it stops just short of a 5.

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