Find paths between positions

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real behavioral context beyond them: routes are restricted to successful technique outcomes only, and when the target is a submission the routes terminate at a position where it can be attempted rather than at the submission itself. That is exactly the kind of semantic quirk the schema cannot express.

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 core action, then the output shape, then the submission special case. Minor deduction: "a few" is vaguer than necessary when max_paths has a documented default of 3.

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, the description steps up by sketching the return shape (each step lists the techniques that achieve it) and the semantics of the submission-target mode. It does not mention path ranking/ordering or what happens when no route exists, which are the remaining gaps for a search tool.

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 goes slightly beyond it by demonstrating the accepted position string form, including role notation ("Half Guard bottom → Back Control top"), and by clarifying that the `to` value may be a submission name — a non-obvious dual-mode input the schema only hints at.

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: "Finds a few shortest routes from one position to another using only successful technique outcomes." The parenthetical example (Half Guard bottom → Back Control top) makes the domain concrete, and the sibling set (search, get_technique, get_position, position_options) has no other path-finding tool, so it is unmistakable.

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 description — call it when you want routes between two positions — but there is no explicit when/when-not guidance or comparison to siblings like bjj_position_options or bjj_search, which an agent could plausibly choose instead. The submission-target case is the only conditional rule given.

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