List Study Runs

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds significant behavioral context beyond annotations: budget is always counted even when paged, missing budget means unknown support, rows you cannot see are simply absent, no totals promised. It doesn't fully describe return object shape but output schema exists and annotations carry the read-only/idempotent load, so a 4 is warranted rather than 5.

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?

The description is dense and efficient, front-loading the core purpose before diving into budget and paging details. Every sentence adds information, and the length is justified by the three parameter behaviors and the budget caveat. It could be trimmed slightly—"Supporting backends" and "recover an uncertain launch" are slightly awkward—but overall it earns a high score.

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?

With an output schema present and annotations covering readOnly/openWorld/idempotent, the description covers the remaining high-stakes context: paging semantics, budget interpretation, capacity recheck, and pagination end condition. It doesn't explicitly state error cases or cursor expiry, but for a list tool with an output schema, this is near-complete.

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 must compensate for the parameters, and it does: limit is explained as opt-in with range 1-200, cursor is explained as opaque token to pass back unchanged, and study_id is implied as the scope of the listing. The description lacks a precise statement that limit without cursor starts from the beginning, but the paging semantics are otherwise clearly tied to the parameters.

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 opens with a specific verb and resource: "List preserved attempts including pending and failed runs." This clearly distinguishes it from siblings like list_runs, get_study_run, and launch_study_run by framing study runs as preserved attempts with statuses included. It goes beyond a vague restatement of the name.

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 description gives explicit paging guidance (opt-in limit 1-200, next_cursor semantics, null means end, no limit returns all rows) and explains when the budget field appears and how to interpret its absence. It warns about capacity recheck and how to recover a launch, which is exactly the kind of when-to-use vs when-not-to-use information an agent needs. No exclusions needed because the sibling set is broad but the scope is clear.

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