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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds crucial behavioral context: the 2026-07-06 cutoff, that new accounts get nothing, and the difference between the list view (lightweight summaries) and detail view (full markdown body). No contradictions 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 verbose (around 200 words) but front-loaded with 'HISTORICAL ONLY' and each sentence contributes meaningful information: alternatives, cutoff date, return formats. No filler, though it could be trimmed slightly without losing substance. Structure is logical – purpose, usage, behavior, parameter modes.

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 read-only tool with one optional parameter and no output schema, the description is exhaustive. It covers when to use, what it returns (both list and detail), the historical limitation, and the migration to get_feed. An agent can call this tool correctly with no further information.

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% (the id parameter already has a description). The tool description adds context by explaining the dual behavior (omit id vs. provide id) in the context of historical data, but it mostly reiterates what the schema states. Still, the clarification of what each mode returns is valuable beyond the schema's one-liner.

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 states a specific verb+resource ('get digests') and clarifies its scope as 'HISTORICAL ONLY' – archived email summaries. It distinguishes itself from siblings like get_feed, get_starred_jobs, and search_jobs by name and purpose, leaving no ambiguity about what this tool is for.

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?

Explicitly states when to use it: 'Reach for this tool only when the user asks about their old email summaries by name.' It also names the alternatives (get_feed, get_starred_jobs, search_jobs) and the conditions that select them, making the decision tree fully transparent.

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