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

Annotations only declare readOnlyHint=false, so the description carries most of the burden, and it does disclose the key trait: calls preview until confirm: true, meaning a default call has no side effect. However, it omits write semantics that matter for a habit log — whether a second call for the same date overwrites or accumulates, what happens if the habit is not assigned to the client, and what the preview returns.

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?

Two compact clauses with the core action front-loaded and the confirm gate appended as a parenthetical caveat. No wasted words, though the parenthetical would read better as a separate sentence stating the preview consequence explicitly.

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 nested-object, two-parameter mutation with only readOnlyHint=false and no output schema, the description covers the confirm-gate but leaves the agent guessing about overwrite vs append behavior, ID sourcing, and what the preview response contains. Adequate to start a call, not adequate to predict its effect.

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 50%: date and clientId are documented in the schema (clientId even points to list_clients), while habitId and completedCount are bare. The description partially compensates by mapping 'completion count for a client on a day' onto completedCount/clientId/date, but adds nothing about habitId (e.g. that it should come from list_client_habits) and nothing about count semantics.

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 (record) plus resource (habit completion count) scoped to a client and a day, and 'on their behalf' signals it is a coach-side write rather than client self-logging, which distinguishes it from list_client_habits, get_habit_compliance and recent_habit_activity. No sibling is named explicitly, so it falls short of a 5.

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?

'On their behalf' implies the coach-logging-for-client scenario and the confirm gate implies a preview-then-commit workflow, but neither is spelled out. There is no explicit when-not guidance, no mention of prerequisites (habit must be assigned to the client first) and no pointer to the alternative tools for reading habit data.

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