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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), and the description adds capability-boundary context the annotations cannot: no USTA band, and no bump prediction is published. Those are exactly the non-obvious behavioral facts an agent needs to avoid fabricating or over-querying, and they go beyond restating the annotation hints.

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?

Three tight sentences, front-loaded with the return content, then the trigger, then the exclusions. Every sentence carries either routing or scope information; nothing is filler or restatement of the name.

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?

No output schema exists, and the description compensates by enumerating the returned fields (level, record splits, model card id, lines behind it). Combined with annotations covering safety and schema covering both parameters, an agent has everything needed to select and call this correctly.

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 100%, so both `player` (name, page link, or number) and `asked` (verbatim question, omit rather than invent) are fully documented in the schema. The description adds only an indirect hint through "when someone asks"; it gives no format or fallback detail for an unresolvable player name, so the baseline 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?

States a specific verb and resource ("Returns the Desk's read of a named player") and then enumerates the payload: Desk level, record by season/team/stage/format, model card id and lines. It also explicitly separates itself from query_roster by saying the USTA band lives on that row, so the agent can distinguish it without opening the sibling 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?

Gives an explicit trigger ("Call it when someone asks how strong a player is, or about their rating, level, trend or bump risk") plus a when-not ("The USTA band is not here... it is the `rating` on a query_roster row") that redirects to the correct sibling. A final note ("The Desk publishes no bump prediction") preempts a query that would otherwise be misrouted here.

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