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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the safety profile is carried structurally. The description adds genuinely useful non-annotation context (requires CREW_LAUNCHER_KEY in MCP env, optional per-key approval, dryRunId requirement). It does not, however, disclose what 'repair' actually overwrites, which is the key behavioral question for a destructive tool.

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 short sentences front-load the core action, with approval details following. Dense jargon ('intent=wire-fees', 'approvalUrl') but no wasted filler, so it is appropriately sized for the tool's complexity.

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, open-world mutation with no output schema and only 56% parameter coverage, the description covers the auth and approval mechanics well but leaves the overlap/replacement semantics and unexplained params (mode, name, ticker) unaddressed.

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 56%, so several parameters (crew, mode, name, ticker) are only partially documented. The description echoes dryRunId usage and ties it to the approval workflow, but adds little meaning for the remaining params beyond what the schema already states.

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 gives a specific verb-plus-resource action ('Create + lock fee-sharing') and scopes it to 'an existing mint', which usefully separates it from launch-time siblings like crew_launch. However, it never names an alternative tool, so an agent still has to infer the boundary against crew_repair-style or launch workflows on its own.

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 supplies real workflow context — 'Approval is optional' and the per-key human-approval path with dryRunId from intent=wire-fees — which implies when the approval branch applies. But there is no explicit when-to-use-this-vs-siblings guidance and no exclusions, leaving the routing decision mostly to inference.

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