begin_work

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

With no annotations, the description carries the full behavioral burden. It discloses only that 'Domain failures are returned as structured error data' and that a stable AUTO-* id is generated when slice_declared_id is omitted. It does not state whether the tool performs writes, what state it creates, permissions required, idempotency, or other mutation-side effects, leaving major behavioral traits undocumented.

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 reasonably concise at four sentences and front-loads the composite purpose before moving to parameter variants and failure behavior. Most sentences earn their place, though the phrase 'without MangoMe jargon' is vague and adds little operational value.

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 18-parameter composite mutation with no annotations, the description is incomplete. Output schema exists, so return values need not be detailed, but the description leaves most parameter semantics, usage versus siblings, and behavioral side effects unexplained, so an agent would struggle to invoke the tool correctly without additional inference.

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 0% across 18 parameters, so the description must compensate. It adds meaning for a few optional parameters — proposed_slice, slice_title, slice_objective, and slice_declared_id — but leaves required parameters (family_id, actor_id, request_text, intent) and many optionals (classification, expected_scope, expected_artifacts, acceptance_expectations, estimate, etc.) completely unexplained.

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 states a composite sequence — 'Compose intake -> plan -> start' — which gives a rough purpose, but the verb 'Compose' is vague and the phrase 'ordinary work without MangoMe jargon' does not clarify scope. It does not distinguish this wrapper from siblings like intake_request, submit_plan, or start_slice, so an agent cannot tell when this tool is preferable to calling those separately.

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 caller-specific parameter guidance — 'Existing callers may pass proposed_slice' versus 'Zero-touch callers can instead pass slice_title' — which is useful. However, it never says when to use this tool versus the many sibling tools such as intake_request, enter_work, or start_slice, nor does it provide any exclusions or prerequisites.

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