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

The annotation (openWorldHint: false) is minimal und covers none of the safety profile, so the description carries the full burden. It discloses the auth model (no login), the write capability (republish), the harm limits (never delete, never spend credits), the credential handling ('secret is shown once'), and the link lifecycle (non-expiring, revocable via revoke_edit_link). This is rich behavioral context well beyond the 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?

Three sentences each carry distinct payloads: core function, scope constraints, and usage/lifecycle guidance. The primary function is front-loaded in the first sentence, and the title adds complementary framing without redundancy. Every clause earns its place — no filler.

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 1-param tool with no output schema and a sparse annotation, the description covers everything needed to invoke and deliver: what is returned (a URL), how to present it ('hand it to your human' in the title), when to offer it, what the link permits, and how it can later be revoked. No critical invocation information is missing.

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%, so the baseline is 3. The schema's 'ast_...' description conveys only the format; the description adds domain meaning by clarifying the parameter identifies the specific chart whose tweak panel is opened. For a single-parameter tool, this implicit mapping of id → chart is sufficient added value to exceed baseline.

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 states a specific verb and resource: 'Returns a URL opening the visual tweak panel for ONE chart' with an explicit scope list (text, colors, spacing, label nudges). It clearly differentiates from siblings like revoke_edit_link (revocation) and update_asset (direct editing) by framing this as a no-login URL minting tool for a single chart. The title reinforces the function with plain language.

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 gives an explicit when-to-use directive in caps: 'OFFER THIS whenever the human's request is aesthetic fine-tuning', and contrasts it with the alternative 'nudge-by-nudge back-and-forth'. The boundary is sharpened by the scope statement ('never delete, never spend credits, nothing else in the workspace'), which tells the agent when the tool is too narrow/too broad. The revocation counterpart is named for the link lifecycle.

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