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

Annotations only say it is a non-read-only, non-destructive write; the description adds the consequential facts an agent must relay: the timeline is saved publicly on the user's page, anyone on the internet can see it, and the agent must tell the user the title and link. It also discloses a behavior the caller cannot control — Time.Graphics picks the text color — and describes what is returned (view, edit and embed links) despite there being no output 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?

Front-loaded with the action and the one-call workflow, then formatting rules, then the disclosure obligation. Every sentence carries information the agent needs and none repeat the name or title.

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 five-parameter write tool with deeply nested event/period objects and no output schema, the description covers what the caller must supply (dates, style book reference), what it cannot control (text color), what happens as a side effect (public visibility) and what comes back (view/edit/embed links). The remaining limits and defaults live in the schema.

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%, so the description has to carry weight; it does explain the tricky part — ISO date strings with negative years for BC ('-0044-03-15' is 15 March 44 BC) — and points to timegraphics://guide for icon types, sizes and colors. It says nothing about the access enum (public/link/private, Premium-gated), the periods date_from/date_to semantics, or the 300-event / 100-period limits, which the schema only partly covers.

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?

States a specific verb and resource ('Create an interactive timeline on the user's Time.Graphics account') and frames it as a one-shot operation, which implicitly separates it from add_events / update_event that mutate an existing timeline. An agent can distinguish this from all ten siblings without opening a 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?

Explicitly scopes usage ('any request to make, build or draw a timeline, chronology, roadmap or history') and gives a workflow instruction: compose all events and periods first, then call once. It does not name the alternative sibling (e.g., add_events for extending an existing timeline), so the exclusion side is left implicit.

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