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

Annotations already declare readOnly/idempotent/non-destructive, so the safety bar is low; the description still adds real value by naming the not-found error for an unknown UUID and by flagging that close_goal is irreversible. It does not cover rate limits or pagination, which is a minor gap for a single-object read.

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?

Front-loaded with the core action, and the routing hints follow logically. The long enumeration of returned fields partly duplicates the output schema, which is mild redundancy, but the fields carry semantic detail (progress 0-1, status examples) that earns most of its space.

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 single-parameter, single-object read with an output schema and full annotations, the description covers action, scope, parameter origin, error behavior, and sibling distinctions. Nothing an agent needs to call it correctly is missing.

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 0%, so the description must carry the burden, and it does: goal_id is described as the goal's UUID, with a pointer to where to obtain it (`id` from list_goals or create_goal). It stops short of stating format constraints or validation rules, so not a full 5.

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 ('Read one goal in full by UUID') and immediately enumerates the fields returned, so the agent knows exactly what it gets. It is clearly distinguished from list_goals, which is described as returning only goal UUIDs.

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?

Explicitly routes the agent: list_goals for UUIDs, get_agent_tasks for the queued steps of the plan, and notes that update_goal/close_goal act on target_state and success_condition. It gives clear context for selection but stops short of an explicit 'use this when you need X instead of Y' rule for every sibling.

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