wave_secret_delete

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

With no annotations, the description carries the full burden and does disclose the Tier C approval gate, the mandatory non-empty reason, and the helper dependency — real behavioral context. It omits that deletion is irreversible and what happens if the key does not exist, which for a destructive mutation would be valuable.

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?

Two short sentences with zero filler; the gate conditions are front-loaded ahead of the dependency note, so the agent reads the blocking requirements first.

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 three-parameter destructive tool with no annotations and no output schema, the description covers the essential gating and dependency facts. A note on irreversibility or failure modes would make it fully self-sufficient.

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%, so the schema already documents key, reason, and approved, and the baseline is 3. The description adds only one extra constraint ('non-empty reason'), which is a marginal gain over the schema text.

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+resource ('Delete a Wave Terminal secret') and is trivially distinguishable from the sibling read/write secret tools (wave_secret_list, wave_secret_set, wave_secret_get). The parenthetical also scopes the operation's gate conditions up front.

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 preconditions for invocation: approved=true, a non-empty reason, and an available Seashell Helper. It does not, however, tell the agent what to do if the helper is unavailable or which sibling to use when the intent is actually to overwrite (wave_secret_set) rather than remove.

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