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

Annotations already establish that this is a read-only, idempotent, non-destructive, closed-world call, so the description's main added value is the cost line (10 credits, Tier 1), the endpoint, and the fact that the band width is expressed in degrees. It says nothing about the default output format or the practical consequence of the format enum, which matters because svg vs json changes what the caller receives.

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 tight sentences front-load the visual concept, followed by compact machine-readable metadata lines. No filler, though the metadata block could have carried the missing guidance instead of just the billing tier.

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?

An output schema exists, so return values need no explanation, but with seven parameters including nested objects and a low schema coverage, the description leaves core ambiguities unresolved: `path` vs `centerlinePoints`, what `options.size/width/height` affect, and whether the graticule defaults on. For a rendering tool with this many knobs, it is under-specified.

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 29%, so the description needs to carry weight and it does not. It explains that bandWidthDeg controls the shaded band, but it never clarifies the relationship between the two near-identical lat/lon arrays, `path` (required, min 2 items) and `centerlinePoints` (optional) — an agent cannot tell which one is the track and which one is the drawn line. Nothing is said about title, options, or how the caller is expected to generate the track in the first place.

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 gives a specific verb and resource: it renders an equirectangular world graticule with a caller-supplied eclipse track, drawing the centerline plus a shaded band of a given degree width. That is enough to distinguish it from analysis-oriented siblings like astroway_geo_eclipse_analysis, though it never names the rendering siblings it competes with (render_star_map, render_timeline).

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?

There is no when-to-use statement at all: nothing says this is the follow-up to an eclipse computation, nor how it differs from astroway_geo_eclipse_analysis or astroway_render_star_map. The [Group: Visualization] tag and the endpoint line imply a render call, but the agent must infer the workflow.

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