onboard_project

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

The description says writes 'are idempotent,' but annotations set idempotentHint to false. This is a direct annotation contradiction, forcing a score of 1 even though the description adds some useful context about save_memory writes.

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 concise and front-loaded, with each sentence contributing distinct information: what is imported, when to call it, the write behavior, and the exclusion of inferred observations.

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 description leaves the confirm parameter entirely unexplained and contradicts the idempotency annotation. While purpose and timing are clear, the missing parameter semantics and conflicting behavioral signal make it incomplete.

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%, and the description never mentions the confirm parameter or explains its meaning. With no schema documentation and no description guidance, an agent has no way to know how to set the only parameter.

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 states a specific verb and resource: 'Import durable facts' from named files like AGENTS.md and CLAUDE.md. It also distinguishes itself from siblings by noting it does not import inferred agent observations.

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 explicit timing with 'Call once on a new workspace' and a when-not with 'Does not import inferred agent observations.' However, it does not explicitly name alternative tools or describe when to use save_memory or capture_activity instead.

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