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

With no annotations, the description carries the full burden and discharges it: it names the events appended (step.fanned_out, child.result, step.joined, child.late_result), the join semantics per policy, that step.joined lands once per (step, attempt), that a failed join routes through retry/escalation, and that budget_exceeded refuses before any child starts or an agent seat is refused. This is unusually rich side-effect and failure disclosure.

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?

Front-loaded with purpose and then organized around the event/join lifecycle; nearly every sentence carries behavioral information. Slightly dense with backtick-formatted event names, but no filler sentences.

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 complex, 7-parameter orchestration tool with no annotations and an existing output schema, the description covers side effects, join outcomes, late results, refusal conditions, and escalation. Return values correctly deferred to the output schema, and nothing an agent needs to invoke it correctly is missing.

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 baseline is 3. The description goes beyond the schema by spelling out what each join value means operationally (all fails on first failure, any completes on first success, quorum needs k of n), which the schema only names as 'all | any | quorum'.

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 (Start) and resource (child instances) scoped to a fan_out step, plus the mechanism by which the step is finished (the join). An agent can distinguish it from process_run_advance, process_run_create, or process_run_complete 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?

Usage is implied rather than stated: the tool is for a step whose actor is fan_out, and the join policy dictates completion. However, it never names an alternative (e.g., process_run_advance for a non-fan_out step) or states when not to call it, so routing still requires inference.

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