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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral information beyond them: the query is an aggregate that 'can take up to 90 seconds by default', warning the agent about latency and hinting the timeout is configurable.

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?

Two sentences, zero waste. The scope and contents come first and the performance caveat is appended rather than buried, so the front-loaded information is what an agent needs to decide.

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?

An output schema exists, so return values need not be explained, yet the description still summarizes them; the latency caveat covers the main operational risk for a no-arg aggregate tool. Nothing essential is missing, though it does not say whether results are cached or how a caller can extend the timeout.

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?

The tool takes zero parameters, which is the baseline-4 case; there is no parameter syntax to explain. The description spends its words on return content and timing instead, which is the right allocation.

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 and resource ('Get favicon statistics across the archive') and enumerates exactly what the aggregate contains: totals, 24-hour counts, and most common hashes with sample URLs. This clearly separates it from per-item siblings like get_favicon and search_by_favicon / search_favicon_mmh3.

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?

Implied usage is legible ('stats' endpoint for archive-wide favicon aggregates), and the 90-second latency note is a real usage consideration. However, no alternative is named and no when/when-not condition is given, so an agent must infer the boundary against get_favicon and search_favicon_mmh3 on its own.

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