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

The description adds critical behavioral information: 'Returns immediately with a new run_id; poll modem_agent_get_run for the result.' This defines the asynchronous nature of the call and the required workflow, which goes beyond the functional guarantees provided by the annotations alone.

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 highly efficient. The first sentence defines the scope (continuation), and the second defines the workflow (immediate response + polling). Both sentences are necessary and well-placed.

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 the richness of the input schema and annotations, the description perfectly covers the remaining operational aspects of the tool. It covers intent, usage context, and execution flow without unnecessary padding.

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 schema coverage is 100%, so the schema itself handles the detailed documentation of parameters. The description successfully frames the parameters within the functional context (e.g., `prompt` is a 'Follow-up prompt'), but adds no semantic value beyond what is already clear in the required fields.

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 specifies the exact function: 'Continue an existing Modem agent conversation.' It sharply distinguishes its purpose from the sibling tool, `modem_agent_invoke`, by stating it is for continuing threads rather than starting new, unrelated runs.

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?

It provides explicit rules for usage and exclusion: it should be used when a question builds upon earlier context, and the agent must use `modem_agent_invoke` for entirely unrelated questions. This prevents common invocation errors.

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