prepare_assignment

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 meaningful behavior: existing Slices are reused and never duplicated, a minimal internal Slice is materialized only when the Family lacks one, and for audit/review it must persist Evidence (planning alone is not completion). That is useful mutation/idempotency context, but it omits permissions, side effects on the assignment, and what 'prepare' actually changes internally.

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 the core purpose, then supporting behavior. Three tight sentences with no obvious padding, though the audit/review sentence drifts toward edge-case policy rather than core function.

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?

An output schema exists, so return values need no explanation. However, for an 11-parameter, high-complexity orchestration tool with zero annotation coverage, the description leaves the entire parameter surface undocumented and does not explain ownership/permission or lifecycle impact. Behavioral intent is covered but the call contract is not.

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 11 parameters, and the description explains none of them. Key fields like family_id, actor_id, request_text, read_only, classification, expected_scope, and expected_artifacts carry no added meaning anywhere. This is a severe gap for a high-arity tool.

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+resource: 'Prepare internal execution for an admitted assignment.' It also clarifies the notable behavior that Slice reuse happens and no duplication occurs, which helps distinguish it from peers that create/generate artifacts. It leans heavily on internal jargon ('MangoMe orchestration', 'Slice', 'Family') and names no sibling, so an agent gets the gist but must infer the domain model.

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?

There is no explicit when-to-use versus a sibling (e.g., start_slice, enter_work, submit_plan). The only conditional is a behavioral expectation ('For audit/review assignments, the worker must still perform the audit and persist Evidence'), which is a completion rule, not selection guidance. No exclusions or alternatives are given.

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