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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description goes beyond them with genuinely useful context: a concrete payload-size warning ("tens of thousands of tokens for a long flow" with elements), the default compact field set, and the hook into get_screen via screenDocId. It stops short of describing pagination or flow-size limits, but the cost disclosure is the operationally important piece.

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?

Three short sentences, front-loaded with the result shape, then the default output fields, then the opt-in expansions with their cost caveat. No filler and no repetition of what the schema already declares.

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?

With only two parameters and no output schema, the description is nearly self-sufficient: it enumerates the compact return fields (screenDocId, pageType, patterns, components, keyTexts), the optional additions, and the cost tradeoff. The remaining omission is provenance for the required flowId.

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 has to carry the semantics, and it does for include — both enum values are explained concretely (OCR/hotspot boxes per step vs. step links) along with the default-empty behavior. flowId is only implied by "One flow"; the description never says what it is or where to obtain one, which is the one real gap.

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?

"One flow with every step in order" states the resource (a single flow), the shape of the result (all steps, ordered), and implicitly distinguishes itself from the plural/list siblings get_app_flows and search_flows. An agent can tell this is a fetch-by-id tool rather than a search tool 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?

It gives clear conditional usage for the include parameter ("compact by default", elements adds boxes, connections adds links) and cross-references get_screen for screenDocId. However it never states when to call this versus get_app_flows or search_flows, or that a flowId must first be obtained from a list/search call — the caller must infer the navigation path from the sibling name alone.

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