get_progress

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

No annotations exist, so the description carries the full disclosure burden. Listing only returned metrics implies a passive read with no side effects, but it never states read-only behavior, data freshness, or that the underlying user can be switched. For a low-risk aggregate read this is adequate but thin.

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 sentences with no filler; the returned-data inventory is front-loaded and the intent trigger is appended. It reads as a field list rather than a purpose statement, but nothing is wasted.

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 and no annotations, the description does well by naming every reported metric, which is the primary missing structured information. It stops short of describing the shape of the response (single object vs. per-topic breakdown) and leaves the sole argument unexplained, so it is serviceable rather than complete.

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 0% for the single user_id parameter, which has a 'default' default. The description never mentions the parameter, whether the default means the current/local user, or that a different user's progress can be requested — a meaningful gap given zero documentation elsewhere.

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 enumerates the concrete payload (XP, streak with freezes, daily goal, per-topic and per-question-type accuracy, weakest topic/type, review queue), which tells an agent exactly what data comes back. There's no leading verb+resource statement naming it as a read of the user's progress aggregate, and it doesn't distinguish itself from the partly-overlapping siblings get_coverage, weekly_recap, or get_due_reviews.

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 supplies explicit natural-language trigger phrases ('how am I doing?' / 'where is my progress?') that map user intent to the tool. There are no when-not conditions and no pointer to the overlapping alternatives such as weekly_recap or get_due_reviews, which an agent would otherwise have to disambiguate itself.

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