update_step

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

Annotations already state this is a non-read-only, non-destructive mutation, so the bar is lower. The description meaningfully adds that 'done' triggers validation gates and returns problems on failure, which is important behavioral context not captured by annotations.

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?

Two tight sentences, front-loaded with the action and followed by the critical gate/retry behavior. There is no wasted text.

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?

An output schema exists, so return-value explanation is unnecessary. The description covers the main workflow and failure loop well, though it could be slightly more complete about non-'done' status behavior.

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 60%, with notes, artifacts, and project_id documented in the schema. The description adds semantics for the 'done' status specifically, but does not explain step_id or the meaning/effects of in_progress, skipped, blocked, and pending.

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 names a specific verb and resource: recording progress on a step and getting the next brief. It clearly distinguishes the tool from a pure read by explaining that marking 'done' triggers the step gate, though it does not explicitly name the sibling next_step as an alternative.

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 clear guidance for the 'done' path: the gate runs, failures return problems, and the agent should fix and retry. However, it does not explain when to use update_step versus next_step or how the other statuses should be chosen.

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