Project onboarding

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

The annotations flag destructiveHint=true and non-idempotent, which would otherwise be surprising for an onboarding call; the description earns credit for explaining why: 'Any call may also log usage, expire transient records and upload owed checkpoints.' It also discloses the untrusted-data security stance, which no structured field carries. It stops short of saying what 'expire transient records' destroys or whether checkpoints gate other calls.

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?

Front-loaded with the core capability, then sibling differentiation, then side effects, then the security note. Dense telegraphic style but no wasted sentences. Slightly clipped in places ('agentFeedback files a feedback row'), yet every sentence carries information.

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?

No output schema exists, and the description compensates by enumerating the sections returned, so an agent knows what it gets. It covers side effects and prompt-injection safety. It does not state prerequisites such as auth or what happens when a project root cannot be inferred, which is the remaining gap.

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 100%, so both parameters are already documented, and the baseline is 3. The description adds only 'agentFeedback files a feedback row' and says nothing about projectRoot inference or feedback side effects. Minimal value beyond the schema.

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?

States a specific verb and resource ('Cold-start onboarding in one call') and enumerates exactly what it returns: project identity, server health, session, work queue, recent decisions, next actions. It also explicitly distinguishes itself from sibling rbook_review ('the shorter everyday start'), so an agent can choose without opening either schema.

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?

Names the alternative (rbook_review) and the condition that selects it: cold start versus everyday start. It also states that agentFeedback files a feedback row, implying when to pass it. Missing an explicit exclusion (e.g., 'do not use mid-session'), which keeps it short of a 5.

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