Set a persistent goal

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

With no annotations, the description carries the full burden. It discloses the persistence behavior ('active across sessions until done'), how goals are surfaced to future sessions, and the update pathway via update_goal. It does not explicitly state whether setting a new goal overwrites an existing one, but the overall lifecycle is well conveyed.

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?

The description is three sentences, front-loaded with the core purpose, and includes a concrete example and references to related tools. Every sentence adds value with 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 simple 3-parameter tool with no output schema or annotations, the description covers the essential context: when to use, persistence behavior, how goals are retrieved, and how to update progress. It is sufficiently complete for an agent to invoke the tool correctly.

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% (only successCriteria has a description), so the description must compensate. It provides a rich example showing the exact format for goal and success criteria, adding semantic meaning beyond the schema. However, projectId is not explained in the description, leaving some ambiguity.

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 clearly states that the tool sets a persistent goal with success criteria that remain active across sessions. It uses a specific verb ('set') and resource ('goal'), and differentiates from sibling tools like update_goal (which updates progress) and get_context/get_project_state (which surface goals).

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 instructs to 'Set one at the start of substantial work', providing a clear when-to-use directive. It also contrasts with read tools (get_context, get_project_state) and the update tool (update_goal), preventing misuse.

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