create_task

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

With no annotations, the description carries the full burden and does disclose real behavior: no agent is started, `criteria` defaults to a specific set (or none when []), and the caller is notified on completion, return, or drop. It omits permission/auth requirements and what actually happens to a task created with local_job or a human work_kind.

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?

Three tight sentences with the core constraint ('starts no agent') front-loaded and parameter notes kept brief via backticks. Every clause carries information; the density is high but readable.

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 6-parameter creation tool with no output schema and no annotations, the description covers the essentials (what is created, criteria defaults, notification behavior) but leaves gaps around local_job/work_kind interaction and repo defaulting that an agent must infer from the schema.

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 coverage is only 33%, so the description must compensate and it partially does: it explains `criteria` semantics with its default value list and gives length guidance for `title` ('about 60 characters'). It says nothing about `repo`, `local_job`, or the `work_kind` values beyond what the schema already states.

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?

States a specific verb and resource ('Create a shared task') and immediately qualifies it with 'starts no agent', which separates it from action-oriented siblings like claim_task or complete_task. It stops short of naming a sibling outright, so it is clear but not maximally disambiguating.

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 'starts no agent' clause implies when this tool is appropriate versus something that would kick off work, and the notification sentence implies it is for delegating/scheduling. However, there is no explicit statement of when to use this instead of ask_people or tell_people, so usage is only implied.

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