Record an observation in the project journal

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

With no annotations, the description carries the burden. It adds a key behavioral note (tool calls are journaled automatically), but doesn't disclose other traits like persistence, editability, or permission requirements. It's adequate but not rich.

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 compact and front-loaded with the main verb and resource, followed by illustrative examples and a behavioral nuance. No redundant filler; each sentence contributes.

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 logging tool with schema coverage and no output schema, the description provides enough context about what to log and how to format it. It doesn't cover edge cases or errors, but those are less critical here.

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 75%, and the description adds meaning beyond it by mapping the 'kind' enum to real-world examples (decision, problem, milestone, note) and illustrating detail format. This helps the agent choose appropriate values.

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 the tool writes to App Factory's journal and gives concrete examples (decisions, problems, milestones, notes). It is specific about the resource and scope, though it doesn't explicitly differentiate from sibling tools like remember or record_answer.

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?

Provides clear usage context: 'Use it for things worth remembering mid-build' with enumerated categories. It also implies a when-not via 'Tool calls are journaled automatically - log the reasoning and events between them,' but doesn't explicitly name alternative tools.

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