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

Without annotations, the description discloses key behavioral traits: SSRF-guarded, https-only, max 5 redirects, and that the response body is never returned. It also explains default behavior (first verify-classed link). Minor omission: no mention of error handling or timeout behavior.

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 a single efficient paragraph with no redundancy. It is front-loaded with the main purpose, followed by selection options, then safety and return format. Every sentence adds value.

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 no output schema, the description provides the return object structure. It covers selection, safety, and behavior. It is slightly incomplete: missing error scenarios (e.g., invalid URL, timeout) or what happens when no link matches the criteria. Otherwise thorough.

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%, but the description adds meaning beyond schema: explains the default for 'class' (verify), mutual exclusivity among url/class/index, and details about the return object's fields. This helps the agent understand parameter interaction and expected output.

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 the tool follows a link server-side ('Follow (server-side GET) a link extracted from a message'), specifies the typical use case ('click the verification link'), and distinguishes from siblings like 'get_links' (list only) and 'follow_sms_link' (follow SMS link).

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?

It provides context for when to use ('click the verification link' step) and explains how to select alternative links via class, index, or exact URL. It does not explicitly list when not to use or mention alternatives, but the guidance is clear for typical use.

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