cos_task_pick

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds behavior context: the tool returns a ranked list (top candidates) rather than a single task, and ranking by priority suggests a selection heuristic. This goes beyond the annotations and helps the agent predict the output shape. No contradictions with annotations.

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, focused sentence of ten words. Every word carries meaning: 'Return' sets the action, 'top candidate tasks' defines the resource, 'start next' clarifies the context, and 'ranked by priority' explains the ordering. It is appropriately concise with no filler or 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?

Given the complexity of 3 optional parameters and a long list of sibling task tools, the description is too sparse. Although an output schema exists (which reduces the need to describe return values), the lack of parameter documentation and usage guidance makes the tool hard to invoke correctly. The description covers only the surface purpose and leaves the agent uninformed about filtering and candidate selection specifics.

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%, and the description does not mention any parameters. The parameter names (swimlane, priority_min, max_candidates) are somewhat self-explanatory but lack details like allowed values, format, or how they affect the ranked results. The description fails to compensate for the lack of schema descriptions, leaving the agent to guess parameter semantics.

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 returns 'top candidate tasks to start next, ranked by priority,' with a specific verb (return) and resource (candidate tasks). This distinguishes it from sibling tools that claim or modify tasks, though it does not explicitly name alternatives. The annotation title 'Pick Next Task to Work On' reinforces the intent.

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 like cos_task_claim_next or cos_task_ready. It does not mention any exclusions, prerequisites, or comparison with other task-related tools. The only implied context is 'to start next,' but that is more purpose than usage guidance.

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