bolt_init_ledger

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

Annotations already declare readOnlyHint=false, idempotentHint=false, destructiveHint=false and openWorldHint=true, so the safety profile is largely supplied structurally. The description adds real value with 'Existing ledgers are preserved,' which clarifies that re-running will not wipe prior state — a meaningful nuance given idempotentHint=false. It still omits what gets created, whether permission or AWS credential access is needed, and any failure modes.

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, front-loaded with the audit category and action, with no filler. It is appropriately sized, though the density of unexplained domain terms means brevity comes at the cost of comprehension rather than being purely efficient.

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 five-parameter mutation tool with no output schema and 20% schema description coverage, the description is too thin: it never explains the return value, the meaning of the buckets, or what customBrains and bannedPatterns do. An agent could invoke it with projectName but would be guessing on the rest.

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 only 20% (only projectPath is documented), so the description must compensate. It briefly echoes 'plumbing slots' but says nothing about projectName, customBrains, bannedPatterns, or the accepted string-vs-object slot forms, leaving four of five parameters with no explanatory help anywhere.

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 names an action (initialize) and a resource (the ledger), plus its audit category, which is more than a tautology. However, the central concept 'three-bucket rules' is unexplained jargon, and an agent cannot tell from the text what a ledger actually contains or how this differs from siblings like bolt_audit_seams or bolt_scaffold_adapter.

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?

There is no guidance on when to call this versus the five sibling audit/registry tools, and no stated prerequisites or preconditions for initialization. The only usage-adjacent statement is that existing ledgers are preserved, which implies it is safe-ish to run on an existing project but doesn't say when to prefer it.

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