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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds valuable behavioral detail beyond annotations: both @SYS short and colon forms are normalized automatically, results span 392K+ label entries, and languages are loaded on-demand with a measurable latency caveat. No contradiction with annotations.

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?

The description is longer than average but every sentence earns its place: core capability, bidirectional examples, normalization note, workflow integration, and language performance. The key facts are front-loaded, and the WORKFLOW section provides actionable guidance without fluff.

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 search tool with no output schema, the description sufficiently explains what is returned (label ID for text searches, localized text for label ID searches) and covers input variants, language behavior, and downstream usage with find_references. Nothing an agent needs to select or invoke this tool correctly 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 adds meaningful semantics beyond the schema by giving concrete examples for the query parameter ('Sales order', '@SYS12345', '@SYS:12345') and clarifying that both label ID forms are accepted and normalized automatically. It also adds operational meaning to the language parameter by explaining startup vs. on-demand loading behavior, though it adds little to maxResults beyond 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?

The description opens with a specific verb and resource ('Search D365 F&O labels') and explains the bidirectional nature: text-to-label-ID and label-ID-to-text. This clearly distinguishes it from siblings like find_references (which consumes label IDs) and search_d365_code (which searches code).

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?

The WORKFLOW section explicitly tells the agent to call search_labels first to resolve label text, then call find_references with the same label ID to find X++ objects. It also gives practical usage context about language loading and the ~15s first-call cost for non-startup languages, which helps agents decide when and how to use the tool.

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