Mark Step

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that screen pixels are ephemeral ('the pixels are gone next turn'), which is a useful context for note-taking. However, it does not disclose other behavioral aspects such as side effects of updating a step, whether the change is reversible, or any permission requirements. It adds some value but remains thin for a state-changing tool.

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 sentences with no wasted words. The purpose is front-loaded, and the note guidance is appended efficiently. Every sentence adds value, and the structure is clean and scannable.

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?

The tool has 4 parameters, no schema descriptions, and no annotations. The description covers purpose and the ephemeral screen context, but it omits parameter meanings for index and device, and doesn't describe expected behavior beyond the status update. While an output schema exists (which might define return values), the input semantics are incomplete. For a tool of this complexity, more context is needed.

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 0%, so the description must explain parameter meanings. It covers 'status' by listing allowed values and explains 'note' as a place to put facts from the screen. However, it does not explain 'index' (likely the step number) or 'device' (which device to target), leaving two of four parameters ambiguous. The partial coverage is insufficient for a tool with no schema descriptions.

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 'Update a plan step' with a specific list of valid status values (pending, in_progress, done, skipped, failed). This is a specific verb-resource pair that distinguishes it from sibling tools like set_plan (which likely creates a plan) and record_finding (which records findings). The purpose is unambiguous.

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?

The description implies when to use it (when updating a plan step's status) but provides no explicit guidance on alternatives or when not to use it. It does offer a practical hint about using 'note' for facts read off the screen, which is a usage consideration, but it doesn't contrast with other plan-related tools like set_plan or record_finding. Clear context exists, but no exclusions or alternative routing.

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