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

Annotations already establish readOnly, idempotent, non-destructive, closed-world. The description adds genuine behavioral detail beyond them: that the PR is always all-time regardless of since_date, that banded and unbanded PRs appear side-by-side, rep-range bests, and that since_date narrows only the Recent block. Some return-content detail overlaps the output schema, keeping this just short of 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?

Strongly front-loaded and organized under USE FOR / NOT for / INFER headers, with the scoping constraint stated first. Slightly long overall, but no sentence is clearly disposable, so a 4 rather than a perfect score.

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 read tool with rich annotations, a full output schema, and three fully documented parameters, nothing an agent needs to invoke it correctly is missing — selection criteria, argument inference, and the since_date/PR interaction are all covered.

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%, so the baseline is 3, but the description earns extra: it clarifies exercise_name resolution (free-text resolved to canonical, or reports if never logged) and reinforces that since_date affects only the Recent block while the PR stays all-time. This adds meaning the schema states only in passing.

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 opening sentence states a precise verb and resource — look up everything for ONE exercise, all-time PR plus recent performance across sessions. It explicitly contrasts against the two most confusable siblings (get_workout for a full session, list_workouts for a date-window list regardless of exercise), so an agent can route to it 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 USE FOR block enumerates three distinct intents with example user phrasings (PR lookups, recent-activity, trend), and the NOT-for section names the exact alternative tools and the condition that selects them. The INFER block further tells the agent which arguments to derive rather than ask for.

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