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

Annotations alone (readOnlyHint=false, idempotentHint=false, destructiveHint=true) are puzzling for a preview call, and the description supplies the key explanation: the image is served from a public share link, which accounts for the side effect and non-idempotency. It still does not explain the destructiveHint=true or whether repeated calls create new links, leaving one annotation unexplained.

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 sentences, no filler: what is returned, how it is delivered, and how the optional parameter changes the output. Front-loaded with the outcome and the trigger phrases.

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 two-parameter image-producing tool with no output schema, the description covers the return artifact (static Gantt with caption), the delivery mechanism (public share link), and the effect of the optional parameter. It omits practical details like the returned URL field or whether the share link is permanent.

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, but the description adds real meaning for `run` — that supplying a run record draws actual bars over the plan — which is more actionable than the schema's own "draws planned versus actual." The `program` parameter gets no elaboration beyond the schema pointer.

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 ("Return a static Gantt image of a program") and reinforces it with user-phrase triggers ("show me a preview", "a picture of the timeline"). It does not explicitly contrast itself with the adjacent siblings visualize_schedule, get_renderer_source, or analyze_schedule, so an agent still has to infer which of those produces an image versus an interactive view.

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?

Gives concrete invocation context via the quoted user utterances and explains the conditional case for the `run` parameter (actual bars over the plan). There is no explicit when-not guidance or named alternative, so an agent choosing between this and visualize_schedule gets no direct help.

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