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

With no annotations, the description carries the burden; it discloses that outputs are sanitized and that latency, credit use, scores, and state are returned, and 'Return' signals a read-oriented operation. It does not explicitly state side effects, auth requirements, or error behavior, but for a status query the disclosed behavior is reasonably complete.

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?

One short sentence lists the return payload in a scannable sequence without filler or repetition. It front-loads the verb and the key output categories and earns each word.

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?

Given a single obvious parameter and an existing output schema, the description covers the main purpose and the kind of data returned. It omits explicit usage/alternative context and parameter provenance, but these are minor for a simple read-status tool.

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 input schema has one required experiment_id with no description (0% coverage), and the tool description does not explain where the ID comes from or its format. Although the name is fairly self-explanatory, the description adds no parameter-level meaning, so it does not compensate for the missing schema descriptions.

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 uses a specific verb ('Return') and names the resource ('AI Workbench Experiment') plus the exact data returned (sanitized model outputs, latency, credit use, scores, experiment state). This clearly identifies the tool as a status/result reader and differentiates it from sibling status tools like swarme_tool_status by focusing on experiment-specific artifacts and metrics.

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?

Usage is implied: an agent needing current experiment results or status would pick this. However, the description gives no explicit condition for when to use it, no exclusions, and no pointer to alternatives such as swarme_experiment_create or swarme_experiment_select_winner, so the agent must infer selection from the tool name and output categories.

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