calculate_spectral_index

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does disclose the no-auth streaming approach ('Streams public COG bands via open HTTP range reads') and the return format ('JSON string with summary statistics, pixel count, and ASCII spatial density visualization'). However, it doesn't disclose failure modes such as behavior when the AOI has no data, what happens when cloud_cover filtering excludes all scenes, or performance implications for large bboxes. Decent but incomplete disclosure for a computational tool with zero annotation safety coverage.

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?

The purpose and Args section are well-structured and front-loaded. However, the References block (four academic citations: Rouse, Tucker, McFeeters, Key & Benson) adds substantial bulk with zero value for tool invocation — an agent doesn't need literature citations to call the tool correctly. That section could be trimmed without losing any operational information.

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?

Given the 5-parameter complexity, 0% schema coverage, and zero annotations, the description is quite complete: it covers purpose, all parameter values/formats/defaults, and the return shape (though an output schema also exists). The main gaps are operational edge cases (empty AOI, all-scenes-filtered-by-cloud-cover, and error behavior), but the core information needed for a correct call is present.

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 0% — the schema properties have no descriptions and no enums. The description fully compensates by documenting every one of the 5 parameters with concrete values and formats: collection ('sentinel-2-l2a' or 'landsat-c2-l2'), index ('NDVI', 'NDWI', 'NBR', or 'EVI'), bbox ('[min_lon, min_lat, max_lon, max_lat] in WGS84'), datetime_range ('2024-06-01/2024-06-30' example), and max_cloud_cover (default 15.0). This gives the agent everything the schema omits.

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 opening sentence states a specific verb+resource: 'compute a spectral index (NDVI, NDWI, NBR, or EVI) for an Area of Interest'. It names the exact indices and collections supported, which distinguishes it clearly from compute siblings like calculate_burn_severity (focused on burn severity) and detect_water_sar (water detection). No ambiguity about what this tool does.

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 highlights 'Zero-config... No API keys or Copernicus account required', which implies this is the tool to use when credentials are absent, but it never explicitly names alternatives or gives when-to-use/when-not-to-use conditions. An agent must infer that, e.g., detect_dark_vessels or analyze_urban_heat_island are the right tools for other analyses rather than being routed to them. The zero-config note is a benefit statement, not a routing rule.

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