ym_set_key

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

The annotations already mark this as non-read-only and idempotent, and the description adds crucial behavioral context beyond those hints: the key enters the chat transcript, the confirmation flag is mandatory, the key is validated against the marketplace, stored locally with chmod 600, and never echoed back. This materially improves an agent's understanding of side effects and risks.

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?

The description is front-loaded with the purpose, then gives a focused security warning, parameter guidance, and postconditions. Every sentence provides useful information; no filler or redundant restatement of the tool name exists, and the `Args` section maps cleanly to the schema.

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 description covers when to use the tool, the security risk, the required confirmation flag, default cabinet behavior, validation, local file permissions, and what happens on success. The main gap is the missing concrete shape of `credentials`, which keeps it from being fully self-contained, but the overall invocation context is otherwise well covered.

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?

The description adds real meaning for `cabinet` and `i_understand_key_goes_to_chat`, including defaults and constraints. However, `credentials`, the only required parameter, is described only as 'dict with the required fields ({fields})' — the actual required fields are left as an unresolved placeholder, and schema coverage is 0%, so the agent still cannot confidently construct the required input.

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 opens with a specific verb and resource: 'Change / rotate the API key from chat'. It also gives concrete trigger examples ('e.g. the old one expired or leaked'), making the tool's purpose unambiguous and distinct from the many set-key siblings by clarifying that this is the chat-based rotation path.

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?

It explicitly says when to reach for this tool ('old one expired or leaked') and names the safer alternative ('the installer, where the key never enters chat'). It also explains the default cabinet behavior so that common cases like 'my key expired' work without extra configuration.

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