Apply Category Suggestions

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

Annotations already declare the safety profile (idempotentHint=true, destructiveHint=false, openWorldHint=true), yet the description adds real behavioral detail the annotations cannot: it refetches and verifies every fingerprint before writing, refuses to auto-apply, and returns a pre-write undo manifest.

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 compact sentences, front-loaded with the core action and its precondition, then the constraints, then the return guarantee. 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 mutating tool with no output schema and full schema description coverage, this covers the action, the precondition, the safety guarantees, the dry-run escape hatch, and the return artifact (undo manifest). Nothing an agent needs to invoke it safely 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 100%, so the baseline is 3; the description still adds meaning by explaining that suggestions must carry fingerprints that are verified and by characterizing dry-run as a pre-write validation step. It stops short of clarifying the budgetId/planId alias relationship or the 25-item cap context, which the schema already covers.

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 (applies) plus resource (explicitly supplied category suggestions) and immediately bounds the scope with the fingerprint-refetch precondition. It is clearly distinguishable from siblings like ynab_auto_assign and ynab_update_transaction.

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 explicit negative guidance: it never auto-applies, approves, or calls TypeSafe, and it supports dry-run. It does not name the alternative tool (e.g. ynab_auto_assign) for auto-application, so the routing is implied rather than spelled out.

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