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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered by structured data. The description adds genuinely new context: an auth/scope requirement (read scope) and an explicit statement of what the tool does NOT do. It stops short of disclosing result ordering, pagination, or result-set size behavior for an open-world listing.

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?

Two compact sentences with the core action front-loaded and the scope/limitation clauses after it. Every clause carries information: ownership scope, required scope, and the two most likely wrong-tool confusions.

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 zero-parameter, read-only listing tool with no output schema, the definition covers purpose, prerequisite, and exclusions adequately. The remaining gap is that it does not say what a listing returns or whether results are bounded, which matters somewhat given openWorldHint=true.

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?

The tool takes zero parameters and the schema is an empty object, so there is nothing for the description to disambiguate. The baseline for a parameterless tool applies, and the description correctly avoids inventing filter arguments that the schema does not support.

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?

"List owned AI training jobs" gives a specific verb (list) and resource (training jobs) with an ownership scope qualifier, which cleanly separates it from write-oriented siblings like emt_start_experiment and emt_rent. It never explicitly names the closely-related singular emt_training_job or emt_training_events, so differentiation of the plural-vs-singular pair is left to inference.

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 supplies a negative boundary ("does not start training or rent GPUs") and a prerequisite ("requires read scope"), which steers an agent away from mutation siblings. However, it gives no positive when-to-use guidance and never points to the alternative tool for starting or inspecting a single job, so the routing decision against emt_training_job or emt_start_experiment is only implied.

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