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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds value beyond them by disclosing result scope (only API-started runs, workspace or key-project scoping), ordering (newest first), and page-at-a-time pagination with a next_cursor round-trip.

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?

Two sentences, front-loaded with scope and ordering, then the pagination instruction. No filler, and the most actionable detail (cursor reuse) lands last where it belongs.

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 an 8-parameter read-only listing tool with no output schema, the description covers scope, ordering and pagination, which are the elements an agent could not read off the schema. Filter semantics are left entirely to the schema, which is acceptable given 88% coverage, though a pointer that filters combine as AND conditions is missing.

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 88%, so the schema already documents the filter and time-bound parameters. The description only reinforces the cursor round-trip ('next_cursor from the previous page'), which largely duplicates the schema's own cursor description, so baseline 3 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?

States a specific verb and resource ('Lists runs') plus meaningful scope ('started through the API in this workspace (or this key's project)') and ordering ('newest first'). It does not name the sibling that returns a single run (get_run), so an agent must infer the distinction, but the plural/scope framing makes the difference reasonably clear.

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?

Gives explicit procedural guidance for pagination ('Pass next_cursor back as cursor for the next page'), which is real usage help. It does not state when to prefer this over get_run or other sibling tools, nor any exclusions, so guidance remains implied beyond the pagination loop.

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