Milli.gold help topics

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful corpus context (~80 articles, Persian content with English URL slugs). It says nothing about result ordering or how many hits come back, which with no output schema is a real remaining gap.

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 short sentences, front-loaded with purpose and followed by the two routing pointers. No 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?

For a one-parameter read tool with no output schema, the description covers what it searches, how to phrase the query, what happens when the query is empty, and which sibling to call next. Nothing an agent needs 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%, so the baseline applies, but the description adds non-obvious meaning: the query matches URL slugs rather than article text, and the examples in the prose ('how to buy, sell, deliver, transfer, verify, fees') show the agent what vocabulary works. That is real value beyond the schema's own 'card' example.

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 ('Find Milli.gold help-center articles') plus the enumerated topic space and the matching mechanism (English keyword). An agent can immediately distinguish this search tool from mg_read (which fetches an article) and mg_fees (the fee table).

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?

Explicitly routes the agent: read results with mg_read, and use mg_fees for the fee table itself. It also pre-empts the obvious failure mode by explaining the articles are Persian but their URLs are English, so English keywords must be used.

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