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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description still earns credit by disclosing the return shape ('rows, columns and nextLink'), which tells the agent how pagination and result inspection work — information not present in the annotations or schema.

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 short sentences with the read-only constraint and return shape front-loaded; little waste. The reference to 'update_canvas_app addDataSource' is the one slightly muddy clause, since that tool is not among the visible siblings, so an agent cannot act on it directly.

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 10-parameter, multi-connector tool with no output schema, the description does enough: it identifies the data sources, flags read-only, and names the return fields including the pagination link. What is missing is connector-specific caveats (e.g. that connector is omitted for Dataverse), though the schema already carries that.

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%, so every parameter including top, skip, filter, select, continuationUrl and connector is already documented at the field level. The description adds only the cross-reference to addDataSource for parameter alignment, which is a minor increment — baseline 3 is appropriate.

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 names a specific verb (read rows) and enumerates the concrete resource types it works against (Dataverse table, SharePoint list, SQL table, Excel table). An agent can tell this is a generic tabular read tool, though the only disambiguation offered is against the out-of-list 'update_canvas_app addDataSource' rather than any actual sibling tool.

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?

It states 'Read-only' and that it takes the same table/connector/dataset/connection as addDataSource, which implies it is the companion read operation to a canvas-app data source binding. But there is no explicit when-to-use versus when-to-use-something-else guidance and no stated preconditions or exclusions.

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