Reports Create Saved Report

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

Annotations already establish readOnlyHint=false, destructiveHint=false, and idempotentHint=false. The description adds a mild side-effect disclosure ('This may create or update Monarch data') that names the mutated system. However, it does not clarify that repeated calls likely create duplicate reports given idempotentHint=false, nor what response to expect. The statement is consistent with the annotations, so no contradiction.

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 short sentences with the purpose front-loaded. The second sentence is vague but earns its place as a side-effect warning. It is appropriately sized for what it communicates, though the vague 'may create or update' phrasing could have been replaced with a more precise statement about persisting report data.

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 write tool with 6 parameters (including a large nested filter object), no output schema, and a rich sibling family, this description is too thin. It does not explain what the tool returns, whether identical names create duplicates, or how it relates to reports_update_saved_report and reports_get_report_data. The ambiguous 'create or update' wording leaves an agent unsure of the operation's exact scope.

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 only 33% (fields and output_mode have descriptions; name, filters, group_by, and timeframe do not). Since coverage is below 50%, the description should compensate, but it adds zero parameter-level information. The nested filters object's field titles are self-explanatory, but the description fails to help an agent choose among name/group_by/timeframe semantics.

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 states a specific verb and resource ('Create saved report'), which is a distinct operation among siblings like reports_get_saved_report, reports_update_saved_report, and reports_delete_saved_report. However, the second sentence 'This may create or update Monarch data' is ambiguous — it could be read as meaning this tool also updates saved reports, which blurs the line with reports_update_saved_report rather than clarifying it as a persistence side-effect warning.

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?

No guidance is provided on when to use this tool versus alternatives. An agent is not told to use reports_update_saved_report for modifying an existing report, reports_get_report_data for computing report data without persisting, or reports_list_saved_reports to check for duplicates first. Usage context is only implied by the verb 'create.'

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