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

With no annotations, the description carries the full burden and largely does so: it discloses the return shape, the prerequisite, downstream call semantics (realign with moves), and constraints like 'do not invent shorthand' and 'ask which leaf if unclear'. It does not state read-only/idempotency explicitly, but the read framing is implicit throughout.

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?

Dense but information-rich; the tier label and trigger condition are front-loaded, and each clause (prerequisite, return, next-step routing, aliasing warning) carries routing value. Some scenarios/Warnings could be tightened, but little is pure filler.

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 not be fully specified, yet the description still names them. Combined with trigger conditions, prerequisites, and next-step guidance, it is nearly complete for a session-scoped selection reader; the only gap is the undocumented guidance_handle.

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 coverage is 0%, so the description must compensate. It gives semantic meaning to map_session_id ('of the open MC') but never mentions guidance_handle at all, leaving one of two parameters undocumented anywhere. Partial compensation, hence a middling score.

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 ('read the latest committed MC session selection') and explicitly distinguishes it from siblings get_part_selection and request_part_selection. An agent can tell what this tool returns (part_layer + part_ids) 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?

Gives explicit trigger conditions (Monica started selection from the legend finger icon, no prior request_part_selection in this turn), prerequisites (open MC's map_session_id), an alternative routing rule (prefer get_part_selection when you have selection_task_id), and even a negative instruction ('Do not resend the TS or request a new selection'). This is textbook when/when-not/alternatives coverage.

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