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

Annotations already declare the safety profile (not readOnly, not destructive, idempotent), so the bar is lower. The description adds genuine value by explaining the trigger events that produce an email (registry updates, new financial statements, deregistration), which is behavioral context not captured in any structured field.

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, front-loaded with the purpose and followed by the behavioral consequence. Every 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?

For a low-complexity, 3-param tool with 100% schema coverage, the description is nearly complete. The one gap is that no output schema exists and the 'get' return shape is never described in prose, though the schema's action description partially covers it.

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 baseline is 3, but the description goes beyond it by explaining the semantic consequence of email_notifications=true (receiving emails on watched-company data changes), adding meaning the schema's terse field description does not.

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 pair ('Get or update') and resource ('email notification preferences for watchlist changes'), clarifying that the tool handles both read and write despite the name 'set_'. No sibling covers notifications, so the agent can place it unambiguously.

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 explains the effect of enabling notifications but gives no explicit when-to-use guidance or when-not-to-use conditions. Usage is implied by the enum in 'action' rather than stated in the description, leaving the routing decision mostly to the schema.

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