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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine behavior beyond that: it returns per-cell data for rendering plus a compact summary of hottest locations in world coordinates, and it flags a mandatory skill-load step. It stops short of noting result size limits or cell-resolution constraints.

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 sentences, each doing work: what it does, what it returns, and the prerequisite. Front-loaded with the action and resource. The skill-load instruction is placed last, which is correct, though it is an operational aside rather than a description of the tool.

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?

The input schema is large and deeply nested, and there is no output schema, so the description usefully compensates by describing the return shape (cells plus a summary with hottest world coordinates). Given the complexity, the main remaining gap is guidance on the heatmap definition itself, which is delegated to list_heatmaps and the skill rather than duplicated here.

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 75% and the important fields (heatmapId, metrics) already carry descriptions in the schema itself. The description reinforces the core semantic — exactly one event whose positions are counted per cell — but adds nothing about time, filters, title, projectId, or environment. Baseline 3 is appropriate when the schema does most of the work.

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 pair ('Build and execute') and a specific resource ('ad-hoc heatmap query'), then defines the semantics: counting one event's recorded positions per heatmap cell. The 'ad-hoc' framing and the pointer to list_heatmaps for the map definition distinguish it from the saved-query siblings (create_heatmap_query/update_heatmap_query) and from get_heatmap_image.

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 an explicit prerequisite ordering: load the heatmap-queries skill before calling. It also implies the trigger condition (you need cell-level position counts for one event on an existing map). It does not explicitly state when-not to use it versus create_heatmap_query or get_heatmap_image, so a 4 rather than a 5.

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