Write the focus board

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

Annotations already flag destructiveHint=true and idempotentHint=true, yet the description adds substantial context beyond them: the board is fully replaced (not merged), a --allow-launchpad permission is required, dry_run is the safe validation path, and the repo must be matched by name reported by launchpad rather than by path to survive across machines.

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?

Three dense sentences with the destructive REPLACE action front-loaded and rules following in priority order; nothing is wasted. Minor cost: '--allow-launchpad' is a CLI-style flag that appears nowhere in the input schema, which could momentarily confuse an agent about whether it is a parameter.

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, non-read-only write with no output schema and partial parameter coverage, the description covers the main risks: overwrite scope, permission gate, validation mode, and data-integrity rules. It does not describe what validation failures look like or what a dry_run report contains, which is a small gap given there is no output schema.

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?

With 50% schema coverage, the description carries real weight: it defines how `repo` values must be formed (name, not path) and imposes a semantic rule on `status` (no done without evidence), plus clarifies that dry_run validates without the launchpad permission. Remaining nested fields like id, title, agent, thread, and the status enum are left to 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 pair and resource: 'Validate and REPLACE the cross-repo focus board.' The REPLACE capitalisation signals whole-board overwrite semantics, and the implicit contrast with read_board (a sibling) is clear from the name and the validate/overwrite framing.

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 concrete operating guidance: use dry_run to validate without --allow-launchpad, and never mark status done without evidence. It does not explicitly say 'use read_board to inspect first' or when not to write at all, so it falls short of full alternative routing, but the conditions it does state are actionable.

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