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

Even with annotations already declaring readOnlyHint, openWorldHint, and idempotentHint, the description adds critical behavioral context: 'it does not call a model, store drafts, or send messages' and 'validates recipients and displays your text.' It also sets content constraints — 'Never invent sender facts, prior meetings, attendance, availability or hiring authority' — which go beyond the annotations. 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 dense but every sentence carries actionable information. It front-loads the core purpose and then layers operational, behavioral, and constraint details without redundancy. The structure is logical and each sentence earns its place.

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?

Given the tool's complexityholcomb, the output schema exists (so return format need not be described), and the annotations cover safety, the description provides all necessary operational context: workflow, constraints, alternatives, exclusions, and behavior. Nothing essential for an agent to invoke it 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 description coverage is 50% (jobId and recipients are documented, while intent and interest are not). The description compensates well for recipients/drafts by explaining the need to pass labeled text and exact public person IDsfake, and it clarifies the max grouping of six. However, it does not add meaning for the 'intent' or 'interest' parameters beyond what the enum values and field names already imply, so the compensation is incomplete.

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: 'Display editable, copyable introductions only when requested.' It then clarifies the tool's scope by stating that it 'validates recipients and displays your text' and what it does not do. This clearly differentiates it from siblings like get_guide_item or search_people.

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 description provides explicit when-to-use guidance ('only when requested'), a required preparation workflow ('First write the drafts yourself... then pass your labeled text'), and direct references to alternatives: 'Fetch missing background with get_guide_item or search_people, not another visual search.' It also gives a precise exception for omitting drafts ('only for 16 planner template options').

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