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

Annotations only declare readOnly/openWorld/non-destructive; the description adds substantial behavior: it really executes the queries, it distinguishes blocking problems from non-blocking warnings and design lint categories, it describes the per-query result shape, and it calls out that sample rows have personal data masked. It also discloses a non-obvious side effect of readOnly semantics via sourcesNotOwned — a dashboard reading a shared connection stays private regardless of sharing, which the annotations cannot convey.

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?

Purpose and the no-publish constraint are front-loaded, and every clause carries information rather than filler. It is, however, two very long sentences with nested parenthetical lists (lint examples, result field list), which makes the key routing signal harder to extract than a short structured layout would.

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 does the work of explaining return values (problems, warnings, per-query columns/types/row count/duration/samples) in enough detail to interpret the response, and it explains the tricky sourcesNotOwned/publishable semantics. The remaining gap is the spec's own shape, which is deferred entirely to dashboard_publish rather than summarized here.

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?

There is one free-form nested spec object whose schema description is circular ('See this tool's description'), and the description never enumerates the spec's fields. It does add one real pointer — 'Use the same spec shape as dashboard_publish' — which is the only guidance on what to pass, so it is better than nothing but leaves the actual structure to another tool.

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?

Names a specific verb pair (validate a spec and actually run its queries) against a specific resource (dashboard spec), and explicitly bounds the scope with 'without publishing anything'. It also points at the sibling whose spec shape it shares (dashboard_publish), so an agent can distinguish it from dashboard_publish/dashboard_promote without opening a schema.

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?

'so you can fix a dashboard before it exists' plus 'without publishing anything' makes the pre-publish use case clear, and the sourcesNotOwned paragraph tells the agent when the sharing caveat must be surfaced to the user. It stops short of an explicit routing rule such as 'call dashboard_check first, then dashboard_publish' or any statement about when this check can be skipped.

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