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

Annotations only cover read-only/idempotent safety; the description adds genuinely new behavior: server-side long-polling up to 40s, ~5 calls for a 3-minute run, the three possible status values, and that the final payload is identical to what the generation call would have returned. It also discloses the scope restriction (answers only for generations started by this agent connection) and the ~5-minute regeneration window, none of which appear in structured fields.

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 trigger condition and the sibling generators, then the mechanics, then the return contract. Dense and largely waste-free, though the Claude Desktop sleep rationale and the semicolon-chained sentences make it heavier than necessary.

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?

No output schema exists, and the description fully compensates: it names the three status values and describes the terminal payload (new design/process/diagram id and counts, placeholder-layout warning, failure reason). Nothing needed to call this correctly is missing.

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 100%, so the baseline is 3; the description goes further by explaining where toolCallId comes from (the "still running" answer) and why waitSeconds should be 30-40 rather than 0 — turning a documented range into actionable guidance with a rationale.

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 (check status of a long-running generation) and immediately enumerates the four generator siblings whose "still running" answers it services. An agent can distinguish this from stride.generate_* tools without opening a 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?

Explicit trigger ("answered 'still running' from stride.generate_ui_design, stride.refine_ui_design, stride.generate_process or stride.generate_diagram"), explicit inputs, and explicit recommended waitSeconds value. It also spells out the counterfactual: calling the generator again while in flight starts nothing, and it restarts only after failure or ~5 minutes.

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