Create a task

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the write nature is known; the description adds real value beyond that by disclosing the permission requirements and the coupling between start: true and an estimate. It does not say what the call returns (e.g. the new task's id) or what happens on partial failure, which are the remaining behavioral gaps.

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 short sentences, with the core action and its permission gate front-loaded and the parameter hints following. The parenthetical permission notes are dense but each sentence carries distinct information; only the opening phrasing ('A new task in your own queue') is slightly elliptical for a tool named create_task.

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 12-parameter mutation tool with no output schema, the description covers the highest-risk ambiguities (permissions, enum-valued fields, start/estimate coupling) but leaves the response contract unstated, so an agent cannot tell whether it receives the new task id for follow-up calls. Several optional fields (acceptance_criteria, planned_start_at) rely entirely on 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 67% and priority has no schema description at all, so the note that category and priority are enumerated values like BUG or HIGH, discoverable per workspace via list_my_tasks, adds genuine meaning the schema lacks. It also clarifies the start/estimate dependency. It still says nothing about acceptance_criteria or the interaction between due_at and planned_start_at defaults.

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 states a concrete outcome ('A new task in your own queue') and names the two permissions that gate it (Take tasks or Create tasks), so an agent knows this is a creation tool scoped to the caller's own queue rather than a general task writer. It does not explicitly contrast with update_task or assign_task, but the 'own queue' scoping does implicitly separate it from assign_task.

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?

It gives a conditional usage rule for start: true (requires an estimate) and routes the agent to list_my_tasks to discover valid category/priority values. However, that reference is for value lookup, not for choosing between sibling tools; there is no explicit statement of when to use create_task versus assign_task or update_task, and no note on preconditions such as workspace selection beyond the schema.

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