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

Annotations already establish that this is a non-read-only, non-destructive, closed-world operation, so the description need not restate safety. It does add real value by disclosing that a *pending* source is created and that a presigned capability is returned, hinting at a multi-step workflow. It omits important behavior: how long the capability lives (expiresIn defaults to 900s), what happens to the pending source if the upload never completes, and any permission requirements.

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?

A single front-loaded sentence that states the action and the outcome with no filler. The trailing file-type enumeration is slightly long but genuinely useful. Nothing 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?

This is a state-creating mutation with a nested five-field required object, no output schema, and zero schema description coverage. An agent still lacks the shape of the returned presigned capability (URL, method, headers), the lifetime of the pending source, and the meaning of required identifiers. For this complexity level the description does too little.

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% and the input is a nested object with five required fields (title, slug, collectionSlug, fileName, fileSize) plus optional expiresIn, contentType and description. The description explains none of these: not what ownerHandle refers to, not the slug format, not that fileSize is capped at 200MB, not the purpose of expiresIn. The file-format list is the only semantic hint, and it is thin compensation for a completely undocumented nested schema.

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 gives a specific two-part verb phrase: create a pending spatial source and return a presigned upload capability. That is concrete enough to distinguish it from a download-preparation or URL-import tool. It stops short of naming the nearest siblings (source_import_url, source_prepare_download) explicitly, so it lands at 4 rather than 5.

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 list of supported GIS file types (GeoJSON, Shapefile, GeoPackage, KML, CSV with coordinates) implies the scenario in which this tool is appropriate. However, there is no explicit statement of when to prefer it over source_import_url or source_prepare_download, and no description of the follow-up step that consumes the presigned capability. Usage is only implied.

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