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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so safety is covered. The description adds genuinely non-obvious behavior: newest-first ordering, cursor pagination, and the fact that list rows omit input/output as {"omitted": true}. It stops short of rate limits or error behavior, but the added context is substantial.

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?

Three dense sentences: the core operation and ordering come first, then filters, then pagination and the row-shape caveat with the escape hatch to runs_get. No filler, and every clause carries information an agent needs.

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 no output schema, the description correctly spends its budget explaining the return shape (summary rows with omitted input/output) and the pagination contract, plus a docs link. A 6-param, zero-required list tool is adequately covered, though the unannotated endpoint/provider filters remain under-explained.

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 only 17%, so the description must carry more weight. It does add value for `task` (exact match, and where to get a task_id) and for cursor pagination, but `endpoint` and `provider` are only named as filter dimensions with no semantics, and `limit`/`cursor` are already documented in the schema. Partial compensation, not full.

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 ('List this workspace's runs'), plus scope ('this workspace's'), ordering ('newest first'), and pagination model. It explicitly differentiates from the sibling runs_get ('runs_get returns the full run'), so an agent can choose between them without opening either schema.

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 concrete filter dimensions (status, provider, endpoint, task) and directs the agent to runs_get when full input/output is needed, and to a prior search to obtain a task_id. No explicit when-not guidance beyond the runs_get handoff, but the routing context is clear.

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