Sdk Edit Undo

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

Annotations already declare the safety profile (not read-only, idempotent, non-destructive). The description adds behavior not in annotations: it requires a valid lease and a confirm=true flag, and it performs the map's *native* undo (state-mutating despite destructiveHint=false). These are genuine extra disclosures.

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?

A single front-loaded sentence: the action first, then prerequisites separated by semicolons. No filler, though the semicolon-packed prerequisites are a little dense for readers.

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 explained, and annotations cover the safety profile. However, with 0% parameter coverage and three undocumented required parameters, the definition leaves an agent guessing about the session/generation guards before invoking a map-state mutation.

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%, so the description must carry the parameter burden. It only clarifies one of four parameters (confirm must be true) and says nothing about sdk_session_ref, expected_map_uri or expected_edit_generation — the concurrency/guard semantics that matter most for a state-changing undo.

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 specific verb and resource: "执行活动地图原生 Undo" (execute the active map's native Undo). This distinguishes it from the edit-family siblings save/discard/redo. It stops short of explicitly naming those alternatives, so it is clear but not fully differentiated.

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?

It gives explicit preconditions for invocation — SDK 编辑开关 (edit switch enabled), 有效租约 (valid lease) and confirm=true. This is usable context for deciding when the call is valid, though it does not state when to prefer Undo over redo/save/discard.

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