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

Annotations already mark this readOnly/idempotent/non-destructive. The description adds crucial context: it opens a browser-local analyzer, returns a hash-bound format-neutral Model IR table and static evidence summary, and provides deterministic views without executing model code. This goes well beyond the annotations and clarifies safety boundaries.

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 sentences packed with distinct pieces of information: trigger condition, supported formats, processing behavior, output artifacts, safety guarantee, and an exclusion list. The trigger condition is front-loaded and no sentence is filler.

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 tool with a rich input schema and output schema, the description provides the necessary operational context: when to invoke, what to pass, what to expect as output, and important exclusions. Missing details like exact return schema are already available in the output schema; the description is complete for selection and invocation.

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 50%: analysis_depth is fully documented in the schema, while file is not. The description compensates by identifying file as the attached deployment artifact (TFLite/ONNX/etc. formats), which gives the agent enough semantic grounding to map the user's attachment to the file parameter. It doesn't detail the OpenAIFile fields, but the object shape is already in the schema.

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 concrete use case ('inspect, summarize, or visualize'), names the exact resource formats (TFLite, ONNX, GGUF, etc.), and contrasts with what it is not ('Do not use for training checkpoints...'). This makes it distinguishable from siblings and clearly tied to the name/title.

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?

Explicitly states when to use ('Use when the user asks...') and provides an explicit exclusion list covering training checkpoints, measured latency, task accuracy, clinical validity, regulatory compliance, and runtime placement. This is strong routing guidance, though it does not name sibling tools as alternatives.

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