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 and delivers: 'newest first' sorting, 'contains-all filters' semantics, and pagination via `meta.next_cursor`. These behavioral details go well beyond what the schema already exposes.

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 two sentences with no filler. The first sentence states the main purpose and use cases; the second clarifies filter behavior and pagination. Every sentence earns its place.

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?

The output schema covers the return shape, and the description covers ordering, filtering semantics, pagination, and use cases. For a simple list tool with well-documented parameters and an output schema, this is 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?

The schema already documents all four parameters with 100% coverage, including the 'include every value given' semantics for sources and keywords. The description adds a concise summary of the contains-all behavior but does not add significant new meaning beyond the schema.

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 'Lists the tenant's past runs, newest first,' which precisely identifies the action, resource, and ordering. It clearly distinguishes this list operation from sibling tools like read_run_status, which targets a specific run.

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 explicitly states when to use the tool: 'find a run whose token you didn't save, or to revisit past analyses.' It provides concrete scenarios but does not name alternative tools or state when not to use it, so it falls short of a 5.

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