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

Annotations only convey idempotent=true, not-read-only, and not-destructive; the description adds genuinely useful behavioral detail: config-based tokens produce a permanent non-expiring connection while pasted tokens are session-only, and no-args invocation returns a link. It doesn't mention whether existing sessions get invalidated, but there is no contradiction with the 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?

At roughly 65 words it is compact, but the structure is poor: it reads like chat support text ('Best: ... Or ...') and buries the agent-relevant invocation contract at the end after branding and human setup instructions. The front-loaded content serves the human user, not the agent selecting the tool.

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 simple tool (1 optional parameter, no output schema, no nested objects), the description covers invocation modes, token format, and persistence semantics. The main gap is not clearly stating what the tool returns in each mode beyond the implied link, and no mention of error behavior.

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 description coverage is 0%, so the description carries the full burden for the single 'token' parameter. It explains that token is a JWT pasted by the user and that omitting it triggers link generation — meaningful compensation. It falls short of 5 by not clarifying return values or invalid-token behavior.

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 identifies the resource (authentication for MCP.AI/IDE agents) and the two core behaviors: returning a login link when called with no args, or accepting a pasted JWT token for session login. It is reasonably distinguishable from the unrelated calculo_* siblings, though it opens with awkward branding and human instructions rather than a crisp verb+resource statement.

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 explicitly contrasts the two auth strategies — permanent config header vs session-only token paste — and states precisely when to call with a token ('after the user pastes') vs without args ('to get the link'). It gives clear conditional context but stops short of naming alternatives or when-not-to-use among siblings.

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