What can I do from here?

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

Annotations already declare readOnlyHint and openWorldHint=false, so the description's job is to add context beyond safety. It does: results are ordered by most-commonly-attempted first, each entry carries a success rate, and each outcome maps to where it leads (success/failure/counter). No auth, rate-limit, or paging behavior is discussed, but the substantive output semantics are disclosed.

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?

One dense sentence with no filler, front-loaded with the verb and resource. It is slightly run-on because the output contract (ordering, success rate, outcome destinations) is packed into the same sentence, but every clause carries 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?

There is no output schema, so the description must describe results, and it does: ordering, success rate, and outcome destinations. With 100% schema coverage on the six (mostly optional) parameters, the gaps are minor — nothing states that role defaults to both or that the position string can encode a slash-suffixed role, though the schema examples cover that.

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% and enums document role, type, and ruleset, so the schema carries the parameter burden. The description's only added semantics are 'in a given role' and the ordering of results; it does not explain how ruleset affects probabilities or how limit interacts with roles. 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: lists transitions and submissions available from a position in a given role. The scope is clearly narrower than a position lookup (bjj_get_position) or a search (bjj_search). It never names a sibling explicitly, so sibling differentiation is only inferable from the scope wording.

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?

Usage is implied by the title 'What can I do from here?' and by the phrase 'from a position in a given role', which suggests pairing with a position lookup. There are no explicit when-to-use/when-not statements and no reference to alternatives such as bjj_get_position or bjj_find_paths, so the agent must infer the routing.

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