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

Annotations already declare write, idempotent, non-destructive, non-open-world, so the safety profile is covered. The description adds genuinely new behavior: the call returns an Undo, setNumber null advances to the next set, and values must come from the user rather than inference. It does not discuss what happens on duplicate/conflicting submissions beyond what the idempotencyKey schema note says.

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?

Short, front-loaded, imperative sentences with no filler. Each clause carries a distinct rule (source of args, no fabrication, unit semantics, optional fields, return Undo, exclusion).

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?

An output schema exists, so return values need not be detailed, yet the description still flags the Undo affordance. For an 8-parameter mutation tool with low schema coverage, the description covers invocation sources, optionality, and the sibling boundary without gaps an agent would need to guess at.

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 only 13%, so the description carries the burden and does: it explains where sessionId and slot come from, that loadUnit accepts the user's unit or 'label' for a machine's own numbers, that rir is included only if stated, and that setNumber null logs the next set. That is meaningful meaning added for nearly every undocumented 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?

States a specific verb and resource ('log' a 'set') plus the trigger condition ('when the person tells you a set they did'). It explicitly names the sibling it is not (edit_set), so an agent can separate logging from correcting 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?

Gives positive selection criteria (the person reports a completed set), the source of each argument (get_today or get_session for session and slot), and an explicit exclusion with the correct alternative ('Do not use to correct a set already logged; use edit_set'). The 'Never invent a number' rule adds a clear prohibition.

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