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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the write/safety profile is covered. The description usefully establishes that calories must be user-supplied rather than estimated, but says nothing about whether a new entry is created versus merged, whether a log can be corrected later via update_log, or how validation bounds (20,000 cal, 1,440 min) fail.

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 sentences, zero filler, with the primary scope assertion front-loaded before the routing hint. Nothing could be removed without losing 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?

With no output schema the description needn't describe returns, and annotations carry the safety profile, so the remaining burden is modest. However, for a 5-parameter write tool with no units stated for the two numeric required fields and no mention of the update_log relationship, the description is adequate but leaves real gaps.

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 60%; activity, logged_at, and tz_offset_min are documented in-schema, so the baseline is 3. The description does not compensate for the undocumented required parameters: it never states that calories_burned is in kcal or that duration_minutes is in minutes, both of which are plausible points of agent error given the 0–20,000 and 1–1,440 bounds.

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 leads with a specific verb and resource ('Log structured exercise') and immediately narrows the scope with the qualifier 'with a known calorie burn.' It also explicitly names the sibling it is not (log_anything), so an agent can distinguish the two 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?

It states an explicit when-not condition and the alternative: 'For an ESTIMATED burn from plain text, use log_anything.' The parenthetical example ('30 minute run') shows the exact shape of input that should route elsewhere, which is unambiguous routing guidance.

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