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

Adds substantial context beyond the annotations: the call consumes credits, may return either a result or a task_id (async behavior), and needs an API key. What it does not disclose is the failure/retry economics — annotations say idempotentHint=false, yet the description never warns that a retry could double-charge, nor how many credits a hire costs.

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 English text is front-loaded and efficient: purpose, prerequisite, return shape, and auth all land in four tight sentences. The full bilingual duplication roughly doubles the length, which is defensible for a multilingual platform but does inflate the payload without adding new information.

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?

With no output schema present, the description carries the return contract itself and does so adequately — either the task output or a task_id to poll. Combined with cost, auth, and workflow-order details, an agent has everything needed to invoke this correctly and interpret the response.

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 description coverage is 100%, so the schema already defines both parameters and the baseline is 3. The description adds only marginal meaning: that agent_id must be sourced from mycel_discover and that prompt should be a natural-language task description, which is close to what the schema fields already say.

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?

States a specific verb and resource ("Hire a Mycel agent to execute a task") plus the outcome ("get the result back"), and explicitly names the two siblings that bracket it in the workflow: mycel_discover for the agent_id and mycel_task_status for polling. An agent can distinguish this from mycel_discover/mycel_task_status without opening any schema.

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?

Gives an explicit prerequisite ordering ("Get agent_id from mycel_discover first, then pass a natural-language prompt") and names the follow-up tool for the async case ("poll with mycel_task_status"). It also covers the access precondition ("Requires an API key") and the self-registration fallback with a concrete endpoint.

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