joist_guide

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

No annotations are supplied, so the description carries the full disclosure burden. It implies a read-only informational lookup and establishes a prerequisite ordering ("Call this first"), but never states whether it is non-mutating, whether it must be re-called per session, or what form the answer takes (a URL, UI steps, a screen list).

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 short sentences with no filler, and the scope parenthetical is placed up front before the directive. Nothing can be trimmed without losing information.

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 one-optional-param, no-output-schema guide tool this is close to sufficient, and the "sign-in link" mention hints at a returned URL. Still, an agent cannot predict whether the result is prose instructions, a link, or a screen inventory, which matters for a tool meant to be called before everything else.

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% and the single "task" parameter is already described there as "What you want done in Joist, in your words"; the description adds nothing about it. It also does not clarify that the parameter is optional (0 required), which is the one piece of meaning the schema leaves implicit.

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 names the domain (Joist) and the concrete contents it covers: screens for estimates, invoices and clients plus the sign-in link. It reads as an orientation/guide tool, which is distinguishable from action-oriented siblings like joist_click or joist_open, though it never says explicitly that it returns guidance text rather than performing an action.

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?

"Call this first" gives an explicit ordering rule relative to the other joist_* tools, which is the single most important usage cue here. It does not say when calling it again is unnecessary or what to do after receiving the guidance, so it stops short of full when/when-not coverage.

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