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

Annotations already carry the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=true, openWorldHint=false), so the description only needs to add context - and it does: it discloses the returned authorization_url/request_id/poll_token, notes that poll_token is 'private', explains plan-selection behavior, and clarifies that the link 'grants no access and starts no tracking by itself', which meaningfully tempers the destructive annotation.

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?

Front-loaded with verb and resource, then ordered by input modes, return values, and caveats - a logical agent-readable sequence with no filler sentences. It runs slightly long, and the free-vs-paid plan sentence is peripheral to invocation, but it earns its place as customer-facing context.

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 5-parameter mutation tool with no output schema and destructive semantics, the description covers the important ground: return values are enumerated (compensating for the missing output schema), the audit_id/audit_key pairing is described as an alternative to site_url, and consent semantics are stated. The undocumented 'client' enum and the lack of any note on timeouts or link expiry keep it short of 5.

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 only 20% (just site_url), so the description must compensate, and it does for 4 of 5 params: it explains audit_id+audit_key as a saved free audit that 'brings the report along', restates site_url as the customer's live https site, and defines customer_approved as a consent record. The 'client' enum parameter (codex/cursor/claude_code/other) is never mentioned, which is the one gap.

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?

Opens with a specific verb and resource - 'Creates a Tyton signup and Connect link for one website' - which immediately separates it from connect, audit_site, and get_signup_status. The scope ('for one website') and the two accepted input paths make the intent unambiguous without opening the schema.

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 two invocation modes ('either a saved free audit (audit_id and audit_key...) or site_url'), which is real routing guidance, and implies get_signup_status is the follow-up for status polling. However, it never names a sibling tool or states when NOT to use this versus connect, begin_audit, or audit_site, leaving the agent to infer the workflow position.

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