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

Since no annotations are provided, the description carries the full burden, and it delivers. It discloses rejection behavior ('the server rejects them otherwise', 'Setting a stage the project has turned off is rejected'), the locked state after deployment, and the human-only transition boundaries. It also explains prerequisite conditions for acceptance/ready statuses (no open tasks or unresolved questions). This is far more transparent than typical tool descriptions.

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 long, but every sentence earns its place by adding either a constraint, a prerequisite, or an exclusion. It front-loads the core action and partial-update rule, then systematically walks through the status workflow. The density is justified by the tool's complexity; no filler or repetition was found.

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?

Given the tool's complex state transitions and lack of annotations/output schema, the description is quite complete: it covers the full progressStatus lifecycle, rejection conditions, human-only actions, locking, and assignment scoping. It does not mention authentication/permissions or return values, but with no output schema those are minor; the state-machine guidance is the critical context and it is thoroughly addressed.

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 22%, so the description must compensate, and it does for the most complex parameters: progressStatus gets a full maturity model with exact conditions for each stage, disabledReason gets clear toggling semantics, and planStatus/active are given a concrete usage pattern. It leaves owner, title, description, and documentId with no added meaning, but those are relatively self-explanatory compared to the status state machine.

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 'Update an epic' – a clear verb+resource statement – and immediately clarifies the partial-update behavior with 'Pass only the fields to change.' It goes beyond the bare action to explain core fields (disabledReason, planStatus, progressStatus), which uniquely distinguishes this from create_epic, get_epic, and list_epics without needing to inspect those schemas.

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?

This is exceptionally strong: it gives explicit when-to-use conditions ('When you start working on an epic set planStatus=now and active=true'), exclusions ('deployed is human-only... never available to agents'), conditional rules ('Moving past that stage to the next one is for the human, unless the user explicitly asks for it'), and a scoping guardrail ('Work only on items assigned to the user unless told otherwise'). It leaves no ambiguity about when this tool should be invoked versus when to refrain.

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