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

Annotations already declare readOnly, idempotent, closed-world, and non-destructive, so the bar is lower, but the description still adds real behavior: it refuses to fabricate a near-match, returns an install command per tier, and omitting `sdk` means no adapter is installed and the answer says which to add. Absence-case and tier-filtering behavior go beyond the annotations.

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 sentences, front-loaded with what the tool does and its outputs, followed by the sdk constraint and a pre-use warning. No filler, though the 'read docs before using it' sentence borders on process advice rather than definition.

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 carries the return-shape burden and does so: suggestions with rationale, matching patterns and screens, and per-tier install commands. Combined with full param coverage and rich annotations, only minor gaps remain, such as result count or how patterns/screens relate to suggestions.

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 100% and already documents all three parameters, including the enum values and the leave-it-out consequences for `sdk` and `tier`. The description largely restates the `sdk` narrowing rule rather than adding new meaning, so the baseline of 3 applies.

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 (suggest) and resource (Candor UI items) plus the full output shape: items, rationale, matching patterns/screens, and install command per tier. It is distinguishable from list_components and search_docs by being a recommendation rather than a lookup, though it never names those siblings explicitly.

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?

Gives clear usage context: pass `sdk` to restrict to that agent SDK's adapter, and it explicitly declines rather than suggesting something close when nothing fits. It also directs the agent to read each suggestion's docs before use. It stops short of naming when to prefer list_components or get_component_docs directly.

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