Manage Tasks

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

Annotations indicate readOnlyHint=false, openWorldHint=false, destructiveHint=false, matching the description's implied mutation operations like 'complete' and 'auto_prune'. The description adds context by detailing what each action does (e.g., 'cancel stale in-progress tasks'), but it doesn't disclose side effects beyond action names, such as reversibility, permission requirements, or rate limits. It does not contradict annotations, and given the annotation coverage, the description is adequate but not rich.

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 paragraph that starts with a clear general statement, then lists each action with a short parenthetical explanation. It's front-loaded and free of fluff, though the long enumeration could be more scannable with line breaks. Still, it is appropriately sized for the tool's scope.

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?

Given the tool's complexity (20 params, no required, no output schema), the description provides a high-level overview of actions but lacks a mapping from actions to parameters. An agent may struggle to know which parameters apply to each action (e.g., task_id for complete, query for find_similar_blockers). While the schema documents each parameter individually, the description doesn't synthesize this information. The description is adequate for initial selection but insufficient for correct invocation without further inference.

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 provides descriptions for all 20 parameters (100% coverage), so the baseline is 3. The description does not add any parameter-specific details; it mentions actions but doesn't map them to parameters. However, since the schema already covers semantics, the description doesn't need to compensate. It offers no extra benefit beyond what the schema provides.

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 tool's purpose: task management via multiple specific actions (next, complete, find_blocked, etc.), each with a brief explanation. The resource (tasks) is explicit and distinct from sibling tools like manage_nodes or manage_snapshots, though it doesn't explicitly contrast them. The listing of actions is informative and covers the main capabilities.

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 no guidance on when to use this tool versus alternatives. It simply enumerates supported actions without mentioning circumstances where a sibling tool would be more appropriate, nor does it state any prerequisites or exclusions. An agent must infer from the tool name that it's for tasks, but there's no explicit routing to help select this over manage_nodes or manage_snapshots.

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