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

Annotations declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so the mutation-but-harmless profile is already structured data. The description still adds real context beyond that: the closed vocabulary, integer-only counts, the batch-budget refusal, and that it 'returns nothing but an acknowledgement' with no output schema to say so. It does not cover what the acknowledgement looks like or what happens on refusal. With annotations already carrying the safety profile, this sits at a solid 3.

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 single most decision-relevant fact (never to answer a question), then payload behaviour, then a closing not-for-models warning. Every sentence carries weight, though 'never to answer a question' and 'answers no question' partly repeat, and the batch/refusal rules are duplicated from the schema descriptions.

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?

For a five-parameter mutation with no output schema, the description covers purpose, payload semantics, validation behaviour, return value ('nothing but an acknowledgement') and the correct alternative tool. Nothing an agent needs in order to decide not to call it, or to call it correctly if it must, 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 earns one more by explaining what the opaque events entries actually are: mount, display mode, safe-area insets, reported heights, keyboard events and one action outcome, which the schema only names as shorthand keys (code, n, c, span, mode, w, h, top, bottom). The 'closed vocabulary, no free text of any kind' line constrains payload shape in a way the permissively-typed additionalProperties object does not.

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 resource (card lifecycle diagnostics) and an explicit scope: 'Used only by the interactive cards this connector draws, never to answer a question.' It enumerates what the payload contains (mount, display mode, safe-area insets, heights, keyboard, action outcome), which makes it unmistakably distinct from the biz_/event_/site_ data tools in the sibling list.

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 an explicit when-not: 'NOT FOR A MODEL TO CALL: it answers no question and looks nothing up,' and names the alternative behaviour: 'Call a data tool instead.' An agent that reaches this tool by mistake is routed correctly without needing to inspect a schema.

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