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

While annotations cover safety (readOnly/idempotent), the description adds valuable behavioral context: it discloses cost ('Free'), return payload ('status and progress'), and the specific state transition condition ('completed') that triggers the next tool in the sequence.

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?

Four efficient sentences with zero waste: purpose ('Check progress...'), return value ('Returns status...'), conditional workflow ('When status...'), input provenance ('batch_id from...'), and cost ('Free'). Information is front-loaded and actionable.

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?

Adequate for a single-parameter status tool. It compensates for the missing output schema by describing the return value ('status and progress'). Could be improved by enumerating possible status values (e.g., pending, running, failed), but the sibling tool integration guidance provides sufficient context for successful invocation.

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?

With 100% schema coverage, the baseline is 3. The description mirrors the schema's guidance about batch_id originating from atlas_start_custom_eval_batch but does not add additional semantic details like format constraints or validation rules beyond the schema.

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 ('Check') and resource ('custom evaluation batch'), clearly distinguishing it from sibling tools like atlas_start_custom_eval_batch (which creates) and atlas_get_custom_eval_batch_results (which fetches final data).

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 defines the workflow: use this tool to check status, and when status='completed', use atlas_get_custom_eval_batch_results. Also specifies the batch_id source (from atlas_start_custom_eval_batch response), preventing confusion about parameter origins.

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