list_runs

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds valuable specificity by enumerating the possible status values (completed/failed/running), but omits safety characteristics (read-only status), performance implications for large directories, or whether the operation is atomic.

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, efficient sentence of 13 words with no redundancy. The parenthetical status enumeration adds precise value without verbosity. Information is front-loaded with the action and target.

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?

Given the absence of an output schema, the description compensates by specifying what information is returned (status categories). For a simple 2-parameter listing tool, this is nearly complete, though explicitly stating the return format (e.g., 'returns an array') would provide full clarity.

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?

The input schema has 100% description coverage, documenting both project_dir and recursive parameters completely. The description focuses on the operation rather than repeating parameter details, which is appropriate when the schema is self-documenting. Baseline score applies.

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 provides a specific verb (scan), target resource (NONMEM run files), and output detail (status categories: completed/failed/running). The scope 'project directory' clearly distinguishes this from sibling tools like check_run_status or get_run_results which likely operate on individual runs.

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?

While the description establishes the context (scanning a project directory), it lacks explicit guidance on when to prefer this over check_run_status for single-run checks or get_run_results for detailed results. Usage is implied by the directory-scanning scope but not explicitly contrasted with alternatives.

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