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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so safety is covered. The description adds genuinely new behavior: results are ordered newest first, each row contains only id and status, and pagination is cursor-based via `before`. It doesn't state what happens when the cursor is invalid or whether filtering requires ownership beyond 'one recipe you own'.

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, zero filler. Scope and default ordering are front-loaded, then filter, then per-row shape with the sibling pointer, then pagination mechanics — a tight, logical progression.

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, return values need not be detailed, yet the description still gives the row shape (id, status). Filtering, ordering, pagination, and the follow-up tool for full detail are all covered, so an agent can call this correctly without opening anything else.

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 0%, so the description must carry the load, and it does: `recipe_id` is explained as narrowing to a single recipe you own, and `before` is explained as the previous page's `next_cursor`. Format details (UUID) live in the schema, and the description does not clarify ordering semantics of the cursor beyond the pagination flow.

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 ('Page through your workflow runs') plus the exact scope: all runs of every recipe by default, or one recipe's runs when `recipe_id` is supplied. It differentiates itself from the sibling get_workflow_run by naming it as the tool for reading a single 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?

Gives explicit routing: use this to page through runs, use `recipe_id` to narrow to one recipe you own, and use get_workflow_run to read one run in full. It also tells the agent exactly how to continue pagination by passing the previous `next_cursor` as `before`.

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