plan_exclusive_latch

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

The readOnlyHint annotation already indicates no mutation, and the description reinforces it with 'does not edit a project.' It adds useful behavioral context about first-press-wins semantics and SET/RSET usage. No contradiction exists between description and 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?

One concise sentence with the key purpose front-loaded and no filler. Every phrase earns its place: preview, recipe type, mechanism, and no-edit guarantee.

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 output schema exists and readOnlyHint is already set, the description is reasonably complete for a preview tool. It conveys purpose, mechanism, and non-mutating behavior. It could benefit from naming the applying sibling, but that is a minor omission.

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?

With 0% schema description coverage, the description must compensate, but it only gives domain context (SET/RSET, first-press-wins). It does not explain what 'participants' should contain or how 'reset_address' is used, leaving two required parameters under-specified.

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 uses a specific verb ('Preview') and resource ('first-press-wins latch recipe'), plus the mechanism (SET/RSET) and scope ('does not edit a project'). It clearly distinguishes this from the sibling apply_exclusive_latch_group, which is the write counterpart.

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 clearly communicates when to use the tool: to preview a recipe without modifying the project. However, it does not explicitly name the alternative tool to use when actually applying the latch, so the usage guidance is strong but not fully explicit.

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