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

Annotations already establish readOnly, idempotent, openWorld and non-destructive behavior, so the remaining burden is lighter. The description goes beyond them with genuinely useful interpretation caveats: direction is monotonic seller-to-buyer (or reverse), scores are ranking heuristics, chained percentages are proportional estimates rather than disclosed exposure, and search limits are reported. These warning-style disclosures meaningfully reduce the chance of an agent misreading the output.

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 dense but purposeful sentences with no filler, and the scope ('one to four disclosed hops') is front-loaded. The phrasing is jargon-heavy ('monotonic seller-to-buyer or its reverse'), which slightly taxes readability, but every sentence carries distinct 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?

For an 11-parameter tool with no output schema, the description does cover per-hop return contents and result-interpretation caveats reasonably well. It nonetheless leaves the bulk of parameter meaning and any sibling routing unexplained, so it is only minimally adequate for a tool of this complexity.

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 only 9% across 11 parameters, so the description should compensate but mostly does not. It hints that depth spans 'one to four hops,' which loosely maps to the depth parameter, but offers nothing for roles, tiers, minPct, minConfidence, ranking, sources, direction or asOf, leaving the agent to guess at filtering and scoring inputs.

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 states a specific action (explore) and resource (supply chain hops of one to four degrees), and lists what each hop carries (source tier, reporting company, quote, filing), so the agent knows this is a graph-traversal tool rather than a flat lookup. However, it never distinguishes itself from the very close siblings company.supply_chain_paths and company.supply_chain_evidence, so an agent cannot tell the three apart from this text alone.

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?

There is no when-to-use guidance, no prerequisites, and no routing to or away from alternatives, despite two obviously related siblings (supply_chain_paths, supply_chain_evidence). The agent is left to infer the selection criteria entirely on its own.

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