bernstein_create_task

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

With no annotations, the description carries the full burden; it does disclose host effects (writes files; makes network requests) and lifecycle behavior (enters backlog, immediately claimable by matching role), which is useful. However it omits whether authentication/permissions are needed, what happens on duplicate or invalid role, and whether the write is reversible.

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?

Three short sentences, front-loaded with the core distinction and the orchestration exclusion, then behavior, then host effects. Nothing is redundant or padded.

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?

Return values are covered by the output schema, so that omission is fine, and the safety/host-effect picture is stated. But for a mutation with 9 largely undocumented parameters and no annotations, the description leaves key invocation details (role matching rules, priority/scope effects, depends_on) unexplained, making it only minimally complete.

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 only 11% — run_id is the sole documented parameter — and the description says nothing about role, model, scope, effort, priority, depends_on, title, or description. For a 9-parameter tool the description should at minimum explain role matching, scope/priority semantics, and depends_on, all of which are left entirely to inference. The detail about claimability by 'matching its role' is the only partial compensation.

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?

A specific verb+resource ('Create a bare task') with an explicit negative scope ('without triggering orchestration or spawning agents') that cleanly separates it from the sibling bernstein_run. An agent can distinguish it from alternatives without opening the 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?

The description gives a clear condition for use (when you want a bare backlog task rather than an orchestrated run) and names the downstream tool, bernstein_claim, that will pick it up. It stops short of explicitly contrasting with bernstein_run, and no exclusions or prerequisites (e.g., role/run_id requirements) are stated.

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