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

No annotations exist, so the description carries the full burden and does so well: it discloses that selection is weighted rather than uniform, that every non-drift mode has a small chance of drifting to an island, and that islands can be left only by drifting again. It omits return shape and any permission/safety notes, but the probabilistic behavior, the key trait for this tool, is thoroughly surfaced.

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?

Front-loaded with purpose, then a compact mode catalogue, with each mode earning its clause. Minor waste in the near-duplicate 'not pure random, but not predictable either' and in the fairly long drift parenthetical, but the structure is sound and readable.

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 zero-required-parameter tool with full schema coverage and no output schema, the definition supplies everything needed to call it correctly: selection semantics, mode meanings, and the probabilistic drift side-effect. Nothing material for invocation is missing.

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 the schema already names the five valid values, so the 3 baseline is set. The description goes beyond that by explaining what each mode actually selects ('tension' = most seeds deposited, 'cold' = high connections/low traces, 'fresh' = most recently seeded, 'drift' = edgeless islands), giving real semantic meaning the one-line schema description does not.

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 action and output: 'Drop into an unexpected corner of the graph' and 'Returns a randomly selected piece weighted by an interesting heuristic.' This clearly positions it against deterministic retrieval siblings like get_piece or search_corpus, since the selection is explicitly non-deterministic.

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 clear context for use ('breaking out of a rut or discovering what you didn't know to look for') and implicitly positions it as the only route to edgeless islands ('reachable only by chance like this'). It does not explicitly name alternatives such as get_piece or search_corpus, so it stops short of full when-not guidance.

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