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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered; the description adds real content by enumerating the returned fields, including the oracle price and per-range crowd probabilities, which tells the agent this is a live read, not a cached snapshot. It says nothing about freshness or rate limits, so it is not exhaustive.

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 plus a four-word instruction. The control-flow hint ('Call this first') is placed at the end where it reads as an action, and no clause is filler.

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 carries the return-value burden and does so by listing every field an agent would need to reason about a market. A one-parameter, one-resource read tool is fully specified by what is given.

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 100% and the single parameter is fully documented with its pattern and default. The description only echoes the 'this week's or past' distinction, so it adds little beyond the schema — baseline 3.

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?

Names a specific verb and resource ('this week's Bitcoin market (or any past one)') and enumerates exactly what the payload contains: question, close time, settlement rule, result, Chainlink price, and range probabilities. That is concrete enough to separate it from list_markets and get_trades without opening a schema.

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?

'Call this first' gives an explicit ordering instruction, and the schema-plus-description pairing routes the agent to list_markets when it needs an address. It stops short of stating when NOT to use it, but the sequencing guidance is unusually direct.

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