task_list

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It discloses ordering ('oldest first'), output truncation ('text truncated to 80 chars'), a dependency ('Requires the fleet Postgres'), and safety ('Read-only'). It does not describe return fields or auth requirements, but the disclosed behaviors are quite specific and useful.

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 three compact, front-loaded sentences. The first sentence states the core function, scope, ordering, and truncation. The second clarifies intended use and names an alternative, and the third adds the dependency and read-only nature. Every sentence earns its place without redundancy.

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?

The description covers purpose, usage, dependency, and read-only safety, which makes it easy to decide when to call. However, it fails to explain the required `app_id` parameter and the `limit` parameter, leaving gaps in invocation knowledge. Since the schema provides no descriptions, these omissions reduce overall completeness for a 3-parameter tool.

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 explain all parameters. It explicitly explains `agent` ('for one worker `agent`') and its default, but it does not explain `app_id` (the only required parameter) or `limit`. This is a significant gap because an agent cannot correctly invoke the tool without knowing what `app_id` represents.

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 a specific verb and resource: 'List tasks still waiting in the Kart queue for one worker `agent`'. It also distinguishes this tool from the sibling `task_status` by noting it returns a summarized queue view, whereas task_status gives one task's full detail.

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 explicitly says when to use this tool: to answer 'what is queued to run', and directs the user to `task_status` for detailed single-task info. It also notes the prerequisite 'Requires the fleet Postgres' and that it is read-only, providing clear context for appropriate use.

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