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

Annotations already declare readOnly, idempotent, non-destructive, non-open-world behavior, so the safety profile is covered. The description usefully adds that the response includes the block plus the components it composes, which is real behavioral context, but it says nothing about source inclusion or response shape.

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 tight sentences with the distinguishing comparison and usage cue front-loaded. Nothing is wasted, though the analogy-first phrasing slightly delays the core subject.

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 no output schema, the description partially compensates by noting the response contains the block and its composed components. However, it leaves includeSource undefined and provides no guidance on slug sourcing beyond what the schema already states, so gaps remain.

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 only 50%: slug is documented (with a pointer to search_components) but includeSource has no description anywhere. The description adds no meaning for either parameter, so it fails to compensate for the coverage 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?

The description states what is retrieved (blocks: full screens and sections) and gives concrete examples (login, settings, pricing pages), and differentiates itself from the sibling get_component via an explicit analogy. It works, though it relies on the agent already understanding get_component rather than naming the verb+resource directly.

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 a clear when-to-use condition: 'Start screens from a block when one fits.' and implicitly positions itself against get_component. There are no explicit when-not conditions or alternatives, but the selection context is unambiguous.

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