Create report

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=false, so safety is covered. The description adds genuinely new behavioral context: the result is organization-private (visibility/auth scoping) and constrained to explicitly identified runs rather than arbitrary scanning. It does not say what is returned or whether repeat calls create duplicates, which matters given idempotentHint=false.

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?

Two sentences, no filler. The positive capability and its scope come first, the exclusion second, so an agent reading only the opening clause still knows what the tool is.

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 create tool with no output schema, the description never says what comes back (a report ID to pass to get_report?) or how the 'explicitly identified evaluation runs' are bound given a completely empty parameter object. Those two omissions leave the agent unable to actually invoke the tool correctly, which outweighs the otherwise useful scope statements.

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?

With zero parameters the baseline would be 4, but the description explicitly promises reports 'over explicitly identified evaluation runs' while the schema has no properties at all – the agent cannot tell how runs are supplied (implicit from prior context? a hidden convention?). That mismatch is a real ambiguity the description creates rather than resolves.

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 ('Create an organization-private saved report') plus the scope of the data it covers ('over explicitly identified evaluation runs'), which separates it from the read-side siblings list_reports and get_report. It stops short of naming those siblings as the contrasting path, so it is clear but not fully differentiated.

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?

The second sentence tells the agent what this tool deliberately will not do ('Public publishing and arbitrary custom dimensions are intentionally unavailable'), which is useful negative scope. However, there is no positive guidance on when to prefer this over list_reports/get_report, no prerequisites, and no indication of what the agent must have on hand before calling it.

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