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

Annotations already declare the mutation and open-world profile, and the description adds genuinely non-obvious behavior: the call does not upload bytes itself but returns a widget plus an external intake URL, both of which should be surfaced to the user, with the URL as the fallback. It stops short of explaining what state the created entry leaves behind or how it can be cancelled or cleaned up.

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 mode-selection guidance is front-loaded and each sentence carries information. Minor waste in the opening 'Use this tool to' framing, and the return-value guidance is buried mid-paragraph rather than surfaced early.

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?

With no output schema, the description correctly carries the burden of describing the return value (widget plus intake URL) and how to present it. Combined with mode selection, the source-file exclusion, and the pointer to the instructions tool, an agent has everything needed to call it and act on the result.

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%, so the baseline is 3, but the description adds mode-level meaning the schema cannot convey: resources is the new-entry path, upload_id the resume path, retry:true forces a fresh ticket, and app_id only scopes without binding or deploying. It also explains the 'MCP version 2.12' value that mcp_version expects.

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 — collect binary app resources — and clarifies the constraint that source files are not accepted. An agent understands the intake flow, though the description never contrasts this with sibling set_app_resources, so the boundary between the two is left to inference.

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?

Explicitly splits the two call modes: declare resources with target_path for a new upload, or pass upload_id to resume, with retry:true for a fresh ticket after a failed transfer. It also routes to get_resource_upload_instructions for the full workflow, but gives no explicit 'do not use when' condition or comparison against set_app_resources.

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