cos_task_create

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

The description discloses valuable behavioral details beyond the annotations: validation against a config file and enum, the effect of ready=True on pullability, and the DoR-satisfying behavior for bug-kind tasks. The annotations only indicate readOnlyHint=false, so the description adds meaningful context about internal 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 four sentences, front-loaded with the core purpose. Every sentence earns its place: the purpose, the preference over YAML, validation behavior, and special-case parameter guidance. There is 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 large parameter count (15) and zero schema-level descriptions, the description covers the essential create workflow but omits the meaning of many optional parameters. It does not explain fields like epic, labels, status, or depends_on. An output schema exists, so return values are not needed, but the description leaves gaps in understanding the full parameter set.

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?

With schema_description_coverage at 0%, the description must compensate for missing parameter explanations. It adds semantic meaning to key parameters (swimlane, kind, ready, acceptance, repro) but leaves many others (epic, labels, status, depends_on, read_first, agent_session) completely unaddressed. This partial coverage is useful but incomplete, earning a mid-range score.

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 function: 'Create a new Scrumban task file + sync to DB.' This is a specific verb+resource combination that distinguishes it from siblings like cos_task_edit or cos_task_move. The description also mentions validation against scrumban-config.yaml and the 8-value enum, further scoping its purpose.

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 'Prefer this over hand-writing YAML,' giving a direct alternative. It also provides situational guidance: when to use ready=True and when to pass acceptance/repro for bug-kind tasks. This clearly communicates the intended use case and when to choose this tool.

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