reports_save

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

Adds real context beyond annotations: validation error codes (unknown_source, invalid_filter_field, columns_empty), the permission gate A24 reports.write, and confirmation that it is idempotent on idempotencyKey, which reinforces idempotentHint=true. However, destructiveHint=true is never addressed – it does not say whether saving a definition with an existing name overwrites or replaces a prior report definition, which is exactly the destructive risk an agent needs flagged.

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?

Dense but front-loaded: the action and its scope come first, followed by validation rules, boundaries against reports_run, idempotency, and the gate. No filler, though the single long run-on sentence could be split so the validation codes and the sibling boundary are easier to scan.

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 save operation with no output schema, it covers inputs, failure modes, permissions, and the sibling boundary. The remaining gap is what the call returns (e.g. an id) and whether re-saving an existing definition overwrites it, the latter being material given destructiveHint=true.

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 0%, so the description carries the burden and largely meets it: source must come from REPORT_SOURCES, filters must name published fields with type-valid operators, columns must be a non-empty subset of published columns including cf: custom fields, and format is constrained to csv|pdf (the schema has no enums). Only name and workspaceId are left unexplained, which are self-evident.

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 and resource ('save a report definition') plus the underlying model ('REPORT_SOURCES read model') and the composition it captures (source + filters + columns + format csv|pdf). It explicitly distinguishes itself from the sibling that renders output ('renders no artifact (that is reports_run)'), so an agent can pick it without inspecting schemas.

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?

Names the alternative and the boundary condition explicitly: define-and-save here, render there ('renders no artifact (that is reports_run)'). It also gives the precondition (gated on A24 reports.write), which tells the agent when a call will fail.

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