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

Beyond the annotations (readOnly/idempotent/openWorld already declare a safe, non-destructive read), the description discloses three things the annotations cannot: an ULTRA plan entitlement gate, a hard coverage window (~11,646 matches, majors-skewed), and the ambiguity fallback that returns candidate names rather than erroring. That is meaningful pre-call context for auth and reachability.

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?

Four sentences, all load-bearing: the first states what the profile contains, the second routes the reader to coverage limits, the third handles ambiguity, the fourth states the plan gate. Metric families are packed into a compact clause rather than prose padding, and the identity of the tool is front-loaded.

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?

An output schema exists, so the description is right not to explain return shapes, and it covers the remaining risk areas: entitlement, coverage skew, and name-resolution failure. The one gap is that a sibling named get_archive_career offers a broadly similar 'career profile', and the description never says which to pick when a player has both archive and charted data.

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; the description earns one extra by explaining the resolution contract for `name` — it must resolve to a single charted person, and an ambiguous fragment yields a candidate list to choose from. The `gender` disambiguator is left entirely to the schema, which is acceptable at full coverage.

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 names a specific resource (career profile) and its distinctive data source (shot-level charting), then enumerates the stat families returned: serve placement, return depth/outcomes, net play, clutch break/game/set-point serving, winners/errors by wing, rally-length tendencies. That is far more specific than the title alone. It does not, however, explicitly distinguish itself from the sibling get_archive_career, so an agent must infer the split from 'shot-level charting data'.

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?

'COVERAGE IS CURATED, not full-slate: 11,646 charted matches back to the 1960s, concentrated on the majors' is a strong when-to-use/when-not signal, and 'An ambiguous name returns the candidates to choose from' tells the agent how to recover from a failed resolution. What is missing is an explicit pointer to the alternative (get_archive_career, get_player) when the player is outside charted coverage.

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