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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial behavioral context: polling semantics, terminal statuses, the non-terminal re-call behavior, and where to find per-run failure reasons. No contradiction with 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?

Every sentence earns its place: purpose, polling behavior, terminal statuses, re-call guidance, per-run result routing, and a documentation link. It is dense but not bloated, and the core purpose is front-loaded.

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?

The description covers what the agent needs to safely and correctly invoke the tool: how to poll, what statuses to expect, what not to do (re-submit), and where to get individual results. The output schema handles return-value details, so nothing critical is missing.

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 batchId, workspaceId, environment, wait, and waitSeconds. The description does not add new parameter-level meaning beyond clarifying the wait behavior, which the schema already covers. 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 states a specific verb ('Get the aggregate status') and resource ('classify batch'), clarifies the related submission tool (run_classify_batch), and distinguishes aggregate status from individual results, which are routed to list_classify_runs. This clearly separates it from sibling tools like get_classify_run and list_classify_runs.

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?

Explicitly says when to re-poll with wait: true, warns not to re-submit the batch, and directs users to list_classify_runs filtered by batchId for per-run failures. This is strong when-to-use/alternative guidance.

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