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

Annotations already declare readOnly, idempotent, closed-world, non-destructive. The description adds information annotations cannot convey: this call is non-blocking (poll vs. wait) and it is 'Free', i.e. consumes no quota. It does not enumerate the possible status values returned, which would complete the picture.

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?

Three short sentences, front-loaded with what the tool returns, followed by the two routing decisions. Nothing is wasted; the cost note is a single word placed where it will be read.

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 one-parameter polling tool with no output schema, the description covers the essential decisions: what it gives you, when to move to results, and when to block instead. The only gap is that the returned status vocabulary and progress shape are unspecified, which matters somewhat given no output schema exists.

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 the schema already says batch_id comes from atlas_start_custom_eval_batch. The description reuses batch_id in the follow-up call examples but adds no new format or constraint detail beyond the schema, so baseline 3 applies.

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 resource (a custom evaluation batch) and what it returns (status and progress), which distinguishes it from atlas_get_custom_eval_batch_results and the start tool. The phrasing 'Progress ... : status and progress' is mildly redundant, but an agent can still tell exactly what this returns.

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 lifecycle routing: when the batch is completed, call atlas_get_custom_eval_batch_results(batch_id); if the caller wants to block, use careerproof_wait(kind='custom_eval_batch', id=batch_id) instead of polling. That is a when-to-use and a when-to-use-something-else in two sentences.

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