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

Annotations (readOnlyHint=false, destructiveHint=false) indicate a non-read-only operation that does not destroy data. The description adds valuable behavioral context: it states GPU inference, time dependent on area, returns GeoJSON, and the job-polling lifecycle including non-cancellation after submission. It does not contradict the annotations and goes well beyond the basic flags.

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 description is well-organized with clear labeled sections (input, area limit, processing, output, flow, and pre-action). Each section carries unique useful information without redundancy. It is slightly long but information-dense; there is minimal fluff. It could be marginally tighter but is already efficient.

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 tool involves GPU inference, job creation, and polling, the description satisfactorily covers all steps: how to specify inputs, what the result is, how to retrieve it (via check_job_status and get_job_result), and the requirement to use preview_analysis beforehand. It lacks only minor details such as error handling or timeouts, but these are not essential for initial selection.

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%, but the description complements it by specifying that 'satellite_id' must be 'sentinel-1', and reinforces area limit (max 30000 km²) with instruction to split otherwise. It also provides a WKT format example and indicates 'orbit_direction' is optional. This adds practical constraints not fully captured in the schema's property stubs.

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 clearly states the tool detects newly constructed buildings within a specified area and date range using Sentinel-1 SAR change detection. It specifies the verb ('detect'), resource ('buildings'), and scope, and the sibling tools (e.g., 'analyze_disappearbuilding') clearly differ in intent, so an agent can easily distinguish 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?

The description provides explicit workflow guidance: it instructs to run 'preview_analysis' beforehand for scope and credit confirmation, obtains user approval, and notes that jobs cannot be canceled after submission. It also mentions area limits and suggests splitting large areas. While it doesn't explicitly contrast with sibling analysis tools, the purpose is self-evident, and file format and process flow are clearly documented.

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