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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=false), the description discloses three non-obvious traits: the session is one-time, it expires in ten minutes, and completion does not settle the invoice. That last point is a genuine side-effect clarification the annotations cannot convey. It stops short of saying what the caller receives (upload URL/token) or what happens if the window lapses.

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?

Two sentences, both earning their place: the first defines the artifact and its lifetime, the second pre-empts the most likely agent misunderstanding about payment status. Nothing is padded and the key constraint is front-loaded.

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?

An output schema exists, so return values need no prose, but this is a 9-parameter mutation with zero schema descriptions and conditional relationships between `jobId`, `invoiceId`, `costItemId` and `kind` that the description never addresses. An agent knows what the tool is for but not how to fill in most of its required inputs correctly.

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 9 parameters, so the description carries the full burden and largely fails. It clarifies only `kind` via its three named evidence types; `idempotencyKey`, `jobId`, `invoiceId`, `costItemId`, `fileName`, `mimeType`, `fileSize` and `note` get no explanation, including the important question of when `invoiceId` or `costItemId` are required for a given `kind`.

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 and resource: 'Creates a one-time, ten-minute secure image upload' for three named evidence types, which map directly to the `kind` enum. It is clear what the tool produces (an upload session, not the file transfer itself), but it never distinguishes itself from the similarly-named sibling `attach_job_file`, leaving the agent to guess which path to use.

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?

Usage is implied by the enumerated artifact types (supplier receipt, customer payment proof, job evidence), which tells the agent this is the pre-upload step for image proof. The closing line 'Uploading proof never marks an invoice as paid' indirectly points at `record_invoice_payment`, but no alternative is named and no when-not-to-use condition is stated.

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