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

Annotations already declare a non-read-only, non-destructive, non-idempotent write, so the safety profile is covered. The description adds real behavior beyond that: the move counts toward the weekly target, setting completes_item ticks the linked plan item and its path step, and past dates are accepted. It stops short of saying what is returned or what happens if a referenced itemId does not exist, which keeps it off a 5.

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 core definition and the sibling routing are front-loaded, and every clause carries information. It is dense with stacked parentheticals ("Classified like a session (pass leverId, stepId, itemId or projectId when known)"), so it reads as crammed rather than elegantly structured, but nothing is truly expendable.

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 9-parameter mutation with no output schema, the description covers the required field, the optional date backfill, the link parameters, and the completes_item side effect. What remains undocumented is the time and area parameters (both described in the schema) and any error behavior for unknown ids, a small residual 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?

With 78% schema coverage the baseline is 3, and the description earns above it: it explains task as "what changed, in plain words," clarifies date may be a past day, and supplies classification guidance for leverId, stepId, itemId and projectId, two of which have no schema description at all. Minor friction: it refers to "item_id" where the parameter is named itemId.

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?

"Record a move: one action toward the aim with no duration" gives a specific verb plus a precise definition of the resource, and the examples (small fix described from the phone, message sent) bound what counts. It explicitly contrasts with add_session, so an agent can separate it from the closest sibling without opening a 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?

The final sentence names the alternative and the selecting condition: "Use it for work that had no timer; use add_session for timed work." It also pre-authorizes backfilling ("Past days are fine (date)") and states the completes_item condition, leaving little to inference.

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