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

Adds substantial behavior beyond the readOnly/openWorld/idempotent annotations: the automatic dataset fallback chain, per-dataset resolutions and geographic coverage limits, negative values meaning sea-floor depth over ocean, and that a point with no data returns status no_data rather than failing the whole call. That last detail is exactly the kind of error-semantics disclosure annotations cannot carry.

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?

One dense paragraph, front-loaded with the core action and batch limit, then progressively less essential coverage detail. Every sentence carries information, though the dataset/resolution inventory is heavy relative to the space it occupies.

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?

With an output schema present, the description need not explain return shapes, and it instead covers the things the schema cannot: coverage regions, resolution differences, fallback behavior, and per-point failure semantics. Nothing needed to call it correctly 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% and the source enum is already documented in detail, so the baseline is 3. The description goes further by explaining what each source actually yields (3DEP 1–30 m; SRTM ~30 m land; Mapzen beyond SRTM and over ocean), giving the agent a reason to pick a non-auto source rather than just an accepted value list.

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 ('look up ground elevation'), plus scope ('up to 100 coordinates in one call'), returned units (meters and feet), and provenance (dataset and resolution per point). The batch-of-points framing distinguishes it from the sibling path/grid/profile tools without needing to name them.

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 clear conditions for the source behavior (3DEP inside US coverage, Open Topo Data elsewhere, SRTM latitude band, Mapzen fallback) and the no_data outcome. It stops short of explicitly naming an alternative among elevation_get_grid / elevation_get_profile / elevation_check_line_of_sight, so the agent must infer the batch-of-discrete-points use case.

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