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

With no annotations, the description carries the full behavioral burden. It does disclose useful traits: blocked_by_relative_ids is additive (only adds links), already-linked ids are refused, and the call is all-or-nothing when an id fails to resolve. However, it says nothing about required permissions beyond the vague "full authorization controls," side effects (notifications, sprint quotas), or reversibility of creation.

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 sentences, front-loaded with the creation action and then the dependency semantics. Every sentence carries information, though the ManageBlockerLinksTool clause is dense and a short parenthetical or example would have been clearer than the run-on description of waiting/blocker roles.

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 15-parameter creation tool with no annotations and no output schema, the description covers the main action, piece types, and the trickiest linkage parameter. Its main gap is that it never says what is returned (e.g., the new piece's relative_id), which matters for chaining follow-up calls, and it leaves authorization mechanics unspecified.

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 100%, so the baseline is 3, but the description adds real meaning beyond the schema for blocked_by_relative_ids — clarifying the direction of the dependency (this piece waits for the listed ids) and contrasting it with ManageBlockerLinksTool's piece_relative_id/blocker_relative_ids orientation. Other params (sprint_id, priority_code, etc.) are left entirely to the schema.

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 opens with a specific verb+resource: "Create new work items (Tasks, Stories, Epics, Recurents) in McpTask.online." It names the concrete piece types and distinguishes the tool from siblings like UpdatePieceTool and ManageBlockerLinksTool by scope (creation vs. link management).

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 an explicit routing rule for dependencies: use blocked_by_relative_ids when declaring a new dependency on creation, and use ManageBlockerLinksTool to manage existing links. That is a clear alternative with a selecting condition, though it covers only the blocker-linking sub-case and offers no exclusions for the creation flow itself (e.g., when to prefer UpdatePieceTool).

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