list_runs

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

No annotations exist, so the description carries the full behavioral burden. It does disclose ordering (newest first) and session scoping, which is real value, but says nothing about pagination, result limits, whether runs can be missing, or what a run entry contains.

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?

One sentence that front-loads the action and appends the two useful qualifiers (scope, ordering). Nothing is wasted and nothing extraneous is present.

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 zero-argument list tool with no output schema, the description covers the essential facts an agent needs to decide to call it. It stops just short of describing the shape of a returned run or any result-size limits.

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 tool takes zero parameters, so there is nothing for the description to clarify; the baseline for a no-parameter tool applies. Schema coverage is 100% trivially.

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+resource ("List the runs") and adds scope ("of this session"), which distinguishes it from a global run listing. It does not explicitly contrast with the sibling get_run, but list-vs-get is strongly implied by the verb.

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 session scope and newest-first ordering imply when this is useful (browsing recent runs), but there is no explicit guidance on when to prefer it over get_run or plot_run. Usage must be inferred from the verb and from sibling names.

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