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

Annotations cover safety profile (readOnly, idempotent, non-destructive). Description adds valuable context: cost ('Free'), return data structure ('per-candidate evaluation scores and dimension breakdowns'), and state prerequisite (must be 'completed'). Does not cover error cases or rate limits.

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?

Five information-dense sentences with zero waste. Front-loaded with purpose, followed by return value, prerequisites, parameter source, and cost. Every sentence earns its place.

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 single-parameter retrieval tool with no output schema, the description adequately covers prerequisites, return value structure, parameter provenance, and cost. Combined with comprehensive annotations and schema, no gaps remain.

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 has 100% description coverage ('Batch ID from atlas_start_custom_eval_batch response'). The description reinforces this source but does not add additional semantic meaning, syntax details, or examples beyond the schema. Baseline 3 is appropriate for high-coverage schemas.

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 clearly states the specific action ('Get all results') and resource ('completed custom eval batch'), and distinguishes itself from the sibling tool atlas_get_custom_eval_batch_status by clarifying this returns actual results (scores and breakdowns) versus status information.

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?

Provides explicit prerequisite ('Confirm status=completed via atlas_get_custom_eval_batch_status first') and parameter sourcing ('batch_id from atlas_start_custom_eval_batch response'), directly naming the sibling tools required for proper workflow sequencing.

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