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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the bar is lower. The description adds real behavioral context beyond them: preview executes up to 4 tiles in parallel (a hard concurrency cap) and returns a deep-link, while describe returns an enriched inventory — useful operational detail.

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 tight bullets plus a one-line inference rule, with the mode list front-loaded. The 'Chat-native dashboard experience' opener is framing rather than information, but the body is dense and waste-free.

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-value burden and does so per mode (relevance scores and recommendations, rendered tile data plus deep-link, enriched inventory). It omits error behavior and what happens when a requested dashboard_id is invalid or tiles fail in preview.

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 67% and the schema already documents mode and question. The description adds the missing semantic layer the schema lacks: how mode is inferred from the presence of question and what each mode value actually does. It does not explain dashboard_id, which is the sole required parameter with no schema description.

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 (run) and resource (dashboard), then enumerates the three modes with what each does, so the agent knows exactly what invoking it produces. The only shortfall is that it never distinguishes itself from the very close sibling run_dashboard_tile, which also runs dashboard tiles.

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 explicit selection rules between its own modes: 'question provided → answer; no question + no mode → describe', and labels answer as the default when a question exists. It does not, however, say when to reach for run_dashboard versus run_dashboard_tile or a purpose-built analysis tool.

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