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

Annotations only flag it as a non-read-only, idempotent, non-destructive mutation, but the description adds real behavioral context: it replaces the existing list, its effect is deferred to the NEXT test, and validation is partial ('an item that cannot be read is refused by name and the rest are kept'). That refusal-by-name semantics is exactly the kind of state detail annotations cannot convey.

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 the core action and constraint, and every sentence carries distinct information (format, replacement, timing, failure behavior, usage trigger). It is a dense single block rather than cleanly segmented, but there is no 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?

For a single-parameter mutation tool with no output schema, the description covers what is required: input grammar, replacement semantics, deferred effect on the next test, partial-failure handling, and the routing trigger. Nothing an agent needs to call it correctly 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 describes 'items' generically, but the description adds the grammar the schema omits: up to 8 items, each a field id from watch_fields or an expression using numbers, + - * /, brackets, and optionally one comparison (< > <= >=). This is material syntax not present in the schema.

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 (Set) and resource (what the trader's strategy tests report at every step, i.e. the watch list), and specifies the accepted input formats. An agent can distinguish it from watch_fields (which supplies field ids) and rehearse without opening any 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?

Gives a concrete trigger ('Use it when the trader says what they want tracked') with a worked example ('watch the RSI and how far price is from the EMA'), plus the follow-up action (offer to rehearse again) and the field source (watch_fields). No explicit exclusion of alternatives, but the routing context is clear.

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