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

With no annotations, the description carries real weight and delivers: it discloses PATCH-style merge behavior ('only what you pass changes'), a destructive sub-behavior ('fields replaces the whole field list'), a downstream side effect (leads land in list_narrator_leads), and cost (free). It stops short of stating permission/ownership requirements or the 12-field cap already in the schema.

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?

Three short fragments, zero filler, with the conceptual framing (what the button is) front-loaded ahead of the mutation semantics. Slightly telegraphic — 'Free.' and 'Leads land in list_narrator_leads.' are terse to the point of ambiguity about scope.

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?

A mutating, 8-parameter tool with no annotations and no output schema needs more than this. The patch semantics and lead-capture side effect are well covered, but the mode-dependent parameters and the required id are left to the schema, which describes almost none of them.

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 only 13% across 8 parameters, so the description must compensate and largely does not. It adds meaning for type (form vs link) and fields (whole-list replacement), but says nothing about linkUrl, buttonText, successMessage, enabled, or linkOpenInNewTab — including which parameters only apply in link mode.

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 explains what the artifact is ('the button viewers see') and that it takes one of two mutually exclusive shapes: a lead form built from fields, or a link. Combined with the title, an agent can tell this sets the presentation CTA, though the description itself never states the verb or the target resource (a presentation agent) explicitly.

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 implies usage through the form-vs-link distinction but never says when to choose a form over a link, what prerequisites exist, or how it relates to set_presentation_slides / set_presentation_look / set_presentation_voice. The agent must infer its place in the presentation-configuration workflow.

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