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

Annotations cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), but the description goes well beyond them: page size (100), that the response carries total/hasMore, that rows are a short projection never full configs/members/billing, and that each kind is gated by its own view permission and errors if unreadable. That last point is operationally critical and cannot be derived from 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?

Four sentences, each with a distinct job: purpose and kinds, filtering/paging mechanics, return shape, then sibling routing. Nothing is repeated and the selection-critical content is front-loaded.

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?

An output schema exists, so return values need no further explanation, yet the description still flags the projection boundary (no members or billing) that an agent would otherwise have to guess at. Combined with the permission-error behavior, nothing needed to invoke 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, but the description adds real meaning beyond it: offset is quantified as '100 a page' with total/hasMore in the response, and the kind parameter is tied to the per-kind permission model. The q parameter's case-insensitive substring match is only restated from the schema, which keeps this below 5.

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 gives a specific verb and resource ('List one kind of item in this workspace') and enumerates the nine kinds inline, so an agent knows exactly what the tool returns without opening the schema. It also states the instrumentation-level purpose ('to pick an id for another tool'), which distinguishes it from read-for-display siblings.

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 routing: 'For media files use search_media; for screens use search_screens; for one playlist's items use get_playlist.' Combined with the positive 'to pick an id for another tool' framing, an agent can decide between this tool and its nearest siblings without inference.

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