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

Annotations already declare readOnly=false, destructive=false, idempotent=true and closed-world, so safety is covered. The description adds genuine behavioral scope beyond that: only today's tasks qualify, and only three task categories are completable. It doesn't describe side effects (streak/performance updates) or error behavior for an already-completed task.

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 short sentences with zero padding, and the actionable scope is front-loaded before the id-provenance detail. Every clause earns its place.

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 single-parameter mutation tool with full annotation coverage and no output schema, the description supplies what an agent needs to select and call it. A brief note on repeat calls or invalid ids would make it fully complete, but the gap is minor.

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% and the task_id property already documents the composite format and its source in get_today. The description's note that the id comes from get_today restates the schema rather than adding new meaning, so the baseline of 3 applies.

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 gives a specific verb ("mark ... done") plus the resource (a task) and enumerates the exact scope: the cardio main task, the flexibility cooldown, or one strength exercise. That reads clearly against siblings like skip_task and unskip_task, which use different verbs on the same resource.

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?

Usage context is clear: this applies to today's tasks only, and the required id is sourced from get_today, which establishes the calling sequence. It stops short of stating exclusions, e.g. that skipping rather than completing uses skip_task, or what to do if a task is already done.

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