plan_ticket_tasks

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

Annotations declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, but the description adds the crucial distinction that only step=publish actually mutates (creates tasks) while prepare merely saves a draft for approval. That side-effect mapping is real value beyond the annotations. It omits whether published tasks are reversible or what happens on re-publish.

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?

Five short sentences, front-loaded with the step enumeration before the workflow narrative. Every sentence carries information about scope or sequencing. Slightly dense but no filler.

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 multi-step, no-output-schema tool with a union-typed request, the description covers the primary workflow an agent needs: which step to start with, what prepare does, and what publish does. The absence of any guidance on handling continuationToken or draft expiration is a minor gap.

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 request object is a discriminated union, so the description carries the burden of explaining the step values. It does so by enumerating read/prepare/view_draft/publish and describing what each does, which the raw const enums do not convey. It says nothing about the per-step fields (ticketId, draftId, tasks, language).

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: turning an Azure Bug/PBI into implementation and testing tasks with hour estimates. This is a concrete transformation, not a restatement of the name. It does not explicitly contrast itself with siblings review_work/review_sonar, so it stops short of a 5.

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?

Gives clear sequential guidance: start with step=read, then step=prepare saves the plan for approval, and only step=publish creates the tasks. This tells an agent how to sequence calls correctly. It stops short of naming when not to use the tool or the sibling alternatives.

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