conduyt_preview_report

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

With no annotations, the description carries the burden and does disclose the two traits that matter most: the definition is UNSAVED (nothing persists) and output is capped at 10 rows. It leaves out permission requirements and what happens on invalid fields/filters.

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, zero filler, with the distinguishing constraint (UNSAVED, 10 rows) front-loaded before the schema pointer.

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 12-parameter tool with nested objects, no output schema, and almost no inline schema descriptions, the definition is thin on what a preview actually returns (rows, columns, validation errors) and relies entirely on the sibling for field semantics. Just about viable, but gaps remain.

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 8% across 12 parameters, including a nested pivot object, and the description adds no parameter-level meaning beyond pointing at conduyt_create_report's field set. That pointer is useful but forces a lookup rather than compensating for the coverage gap.

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 (Run), a specific resource (an UNSAVED report definition), and the exact scope (10 rows) and intent (check columns and filters before saving). This clearly separates it from conduyt_create_report (persists) and conduyt_run_report (runs a saved one).

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?

"before saving" gives a clear trigger condition for choosing this over creating a report outright, and "Same fields as conduyt_create_report" tells the agent the payload shape is shared. It stops short of explicitly naming conduyt_create_report/conduyt_run_report as the alternatives for the save/run cases.

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