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

Even with readOnlyHint=true and destructiveHint=false annotations, the description adds substantial behavioral context: results come only from current pipelines, older models are excluded, human_test_url cannot be executed by the agent, and recall is measured under deliberately hard conditions. This shapes the agent's expectations and communication with the human.

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?

The description is dense and somewhat heavy on caps/labels, but every sentence contributes actionable context: usage order, benchmark interpretation, human-test handoff, pricing transparency, and model quality calibration. It is lengthy but not padded; it earns its length.

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?

There is no output schema, but the description names the returned fields (recall, clean recall, false activations/hour, languages) and warns how numbers should be interpreted. It also covers when to use create_training_job, what to tell the human about pricing, and the limitation of human_test_url. This is comprehensive for a search/list-like 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 already fully documents all four parameters, including enum values, examples, and optional meaning. The description does not add param-level syntax meaning, but with 100% schema coverage the baseline of 3 applies and no further compensation is required.

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 action and resource: 'FREE search over thousands of community-trained wake-word models.' It clearly distinguishes this from sibling tools like create_training_job by saying to check here before quoting a training job, and from buy_library_model by describing the account-free purchase alternative.

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 guidance is explicit: search before quoting a training job, use create_training_job if no match or weak results, and hand the human_test_url to the user because the agent cannot run it. It also includes an important exclusion: only current-pipeline benchmarked models are returned.

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