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

The annotations already declare `readOnlyHint: true`, `destructiveHint: false`, and `openWorldHint: false`. The description adds meaningful behavioral clarity by explicitly saying it lists without running anything, which prevents confusion with run-starting tools, and by distinguishing app-held runs from caller-supplied run files.

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 a single front-loaded sentence with no filler. The parenthetical explaining HTTP/MCP caller usage is dense but purposeful, and the core distinction arrives before the alternative modes.

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 full parameter description coverage, the definition does not need to explain return values. It covers the essential behavior for this listing tool, though it could more explicitly connect the two modes to practical selection of `runs` versus leaving it unset.

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 100%, so the schema already documents `runs`, `_files`, and `_subject`. The description reinforces the `runs` semantics and unset behavior, but it does not add meaning beyond the schema for `_files` or `_subject`; baseline 3 is appropriate.

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 uses a specific verb and resource, 'List research runs', and immediately clarifies that nothing is executed. It distinguishes the tool from run-executing siblings with 'without running anything' and explains the two listing modes: project-held runs versus supplied run files.

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?

It gives clear usage context: omit `runs` in the app to list the project's runs, or pass `runs` for an HTTP/MCP caller to list kept files. It does not explicitly name alternatives such as `research_run_status` or `cancel_research_run`, nor does it state when not to use this tool.

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