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

Annotations already declare this as a non-read-only, non-destructive, closed-world mutation, so the safety profile is covered. The description adds genuinely new behavior: partial-update semantics and the fact that the changelog is public, implying edits are auditable and attributed. It says nothing about permissions beyond api_key or about what happens to fields left unset beyond the schema's empty-string defaults.

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?

It is front-loaded with the patch constraint and the change_note dependency, the two things most likely to cause a bad call, before dropping into the example. The inline JSON example is long but earns its space given a free-form object parameter, though the prose is dense and slightly run-on in places.

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?

The output schema exists, so return values need no explanation, and annotations cover the mutation profile. However, for a 13-parameter mutation tool with 0% schema coverage, the description leaves most fields undefined and never explains delay_seconds or the free-text fields, which an agent cannot populate meaningfully from this definition alone.

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 0% across 13 parameters, so the description must carry the load and it only annotates three: rules (with a concrete nested example covering markets, min_notional, max_notional, hours_utc, order_type, sides), tag (1-6 lowercase alphanumerics), and change_note (conditionally required). The remaining ten fields, notably delay_seconds, sizing_risk, what_can_go_wrong, category, and idea, get no semantic explanation at all, leaving a substantial gap despite the strong rules 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?

"Change your strategy" gives a specific verb plus resource, and "only the fields you pass change" immediately pins down patch semantics, which is the key differentiator from create_strategy or get_strategy. It never names those siblings explicitly, so an agent must infer the routing from the tool name 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?

The description supplies a real conditional rule: change_note is required when entry/exit rules or recognition rules change, which tells the agent when the call will be rejected. It stops short of stating when to prefer this over create_strategy or when updating is inappropriate.

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