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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description adds valuable behavioral context: cursor-paginated, newest-first ordering, and exact-match semantics for the task filter. This goes beyond what annotations provide and helps the agent understand the tool's behavior.

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 a single, dense sentence that front-loads the core action and filtering capabilities, then adds pagination and a docs link. No fluff or repetition; every clause adds value.

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 read-only list tool with optional filters and no output schema, the description covers essential invocation details: scope, ordering, filtering options, pagination, and a specific hint about using task_id from search. The only missing detail (e.g., default limit) is available in the schema, and the docs link provides further reference. The description is complete for correct usage.

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 description coverage is 0%, meaning the description must compensate for explaining parameters. It names the filterable fields (status, provider, endpoint, task) and clarifies task uses exact match. It also mentions cursor-paginated, implying cursor/limit usage. However, it does not explain the expected formats (e.g., status enum values, endpoint/provider patterns) or the limit's default/max, leaving some gaps. The schema itself provides descriptions only for task, so partial compensation.

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 clearly states the verb (List) and the resource (this workspace's runs), and specifies ordering (newest first). It distinguishes from siblings like runs_get (single run) and run (likely starting a run) by framing this as the list operation. The scope (workspace) is explicit.

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 provides clear context on when to use this tool: to list multiple runs with optional filters. It gives a specific usage hint for the task filter (use a task_id from a search), which guides correct invocation. However, it does not explicitly state when not to use it or mention alternatives by name, though the sibling list implies a distinction.

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