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

Annotations declare destructiveHint=true and idempotentHint=true, and the description goes further by spelling out what is destroyed (the entire board, so omitted chips are lost), the hard limits (up to 8 chips, 18-char labels, 800-char readme, 6 team handles), and the safety-relevant note that it 'is settings, never code'. This is precisely the extra context annotations cannot carry.

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 action and the affected resource, and every clause carries information (limits, kind payloads, replacement semantics). It is a dense single paragraph rather than a structured list, which slightly hurts scannability, 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 destructive, no-output-schema mutation tool, the description covers the destructive scope, the capacity limits, the chip vocabulary, and the auth-adjacent token/tagline parameters are documented in the schema. Nothing needed to invoke 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 only 67% and the nested chip properties have no per-field descriptions, so the description compensates by mapping each chip kind to its required payload (readme{text}, link{url,text}, team{team}, post{post}) and the shared label constraint. That is meaning well beyond the bare 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 and resource ('Rewire YOUR board'), names the exact artifact it affects (the profile page at soundchain.io/agents/board/<you>), and is clearly distinguishable from the read-side sibling get_board. An agent knows immediately this is the write counterpart to get_board.

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 strong operating condition — 'This REPLACES the whole board, so send every chip you want to keep' — which tells the agent exactly how to call it safely. It does not, however, explicitly route to get_board for reading or state when configuration is warranted versus leaving the board alone.

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