rush_continuity

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

With no annotations, the description must carry behavioral disclosure itself. It communicates one critical side-effect (saving writes to cache only with explicit permission) and clarifies the local scope. It does not explain what restore overwrites or how the coordination/provider_resume modes behave, leaving significant behavioral opacity.

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?

Two short sentences, front-loaded with the core action and no filler. The return-shape note and permission caveat each add something an agent needs to know. It loses no points on conciseness, though the first sentence is incomplete about the full operation set.

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?

Given 23 parameters, a 9-value operation enum, no annotations, and roughly 60 sibling tools, this two-sentence description cannot be contextually complete. It omits six operation modes, does not specify which parameters apply to which operation, and does not address coordination or provider-resume behavior. The output schema covers return shape, but not the usage context.

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 needed to compensate for 23 undocumented parameters. It only suggests that saving requires cache-write permission and that the checkpoint is local; most parameters—path, name, files, token_budget, and operation-specific fields—are left unexplained. This is minimal compensation for a very large schema.

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 verbs save/list/restore and the resource 'local Rush session checkpoint' name a concrete core action, so it is not a tautology. However, the operation enum exposes six additional modes (context_pack, context_retrieve, coordination_*, provider_resume) that the description never mentions, making the stated purpose partial and potentially misleading. It also does not differentiate this tool from the many sibling rush_context and rush_mesh tools.

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?

No sentence tells an agent when to prefer rush_continuity over a sibling or which operation mode fits which scenario. The 'local' qualifier and cache-write permission note hint at some conditions, but there are no explicit alternatives, exclusions, or workflow guidance for a tool with nine operational modes.

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