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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely new context: the export is asynchronous and the output is a PNG, and 'create or reuse' explains the idempotent behavior in practical terms. It does not say what is returned (a job/export identifier), how long it takes, or that the result must be fetched separately, which is the key behavioral fact for an async tool.

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 front-loaded sentence with zero padding, which is efficient. It is arguably under-sized for a tool whose schema contains a large nested options object, but nothing in the sentence is wasted.

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?

There is no output schema and no annotation covering return shape, so the description should explain what an export request yields (an export/job id) and how to retrieve the finished PNG. Combined with a deeply nested options object that has zero parameter documentation, the single sentence is not sufficient for correct invocation.

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% across all three parameters, and the nested 'options' object exposes roughly ten sub-fields (view, scale, theme, title, width, height, legend, compass, hiddenLayerIds) that are entirely undocumented. 'A project map or published map' loosely maps to the resourceType enum values project/map, but that is the only semantic contribution; resourceId format, view modes (static vs bounds), and all rendering options are left to the agent to reverse-engineer.

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 uses a specific verb pair ('create or reuse') and names the concrete artifact (an asynchronous PNG image export) and its inputs (a project map or published map). It implicitly separates itself from the sibling map_image_export_status via the word 'asynchronous', but never names that sibling, so differentiation is inferential rather than explicit.

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 statement of when to call this versus map_image_export_status or map_publication_activate, no prerequisites (e.g. the map must be published or validated first), and no follow-up guidance on polling the status tool. The only hint is the adjective 'asynchronous', which the agent must interpret on its own.

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