labels

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

Annotations already indicate destructiveHint=true and readOnlyHint=false, matching the description's explicit 'write' tags for create, update, rename. The description adds valuable behavioral detail: create writes to every language .label.txt, update overwrites existing text, rename affects multiple file types, bulk mode behavior (failed entry doesn't abort batch), and auto-resolution of write plumbing. This is transparent and adds context beyond 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 well-structured with a clear introductory sentence, bulleted action items, and explicit parameter usage notes. Despite its length, every sentence serves a purpose—either defining an action, clarifying input formats, or providing operational tips (e.g., bulk mode, createIfMissing). It is organized for quick scanning and front-loads the core purpose.

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 tool with 14 parameters and multiple actions, the description covers all critical aspects: per-action parameter requirements, edge cases (bulk failures, missing labelId), write plumbing auto-resolution and override path, and safety (dryRun for rename). It also cross-references get_knowledge for deeper details, ensuring an agent has enough context to invoke correctly without an output schema.

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: labelId accepts various spellings (SYS67433, @SYS67433, @ContosoExt:MyLabel) and clarifies that omitting it lists label files; labels[] explains bulk mode and top-level field suppression; params explains auto-resolution and points to get_knowledge for contract. These additions raise it above the baseline, but not maximal since some parameters (e.g., verbose, maxResults) rely on schema descriptions without extra context.

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 clearly states it is a unified label operations tool with read/write actions and enumerates each action (search, info, create, update, rename) with concise purpose statements. It distinguishes these actions from each other and from sibling tools by focusing on label-specific operations, making the tool's purpose unambiguous.

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?

Provides explicit guidance for when to use each action, including required parameters, examples (e.g., createIfMissing for reuse, bulk mode via labels[]), and even advises dryRun for rename. It clarifies when to use create versus update and how to override auto-resolved write plumbing via get_knowledge, giving clear operational context.

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