upload_file_from_url

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

Annotations provide destructiveHint=true, but the description does not contradict it; it simply adds rich behavioral context beyond annotations: SSRF protection (refusing private/loopback IPs), max source size (10 MiB), accepted formats, transcoding to PNG when purpose is supplied, and generation of 1x/2x/3x variants. It also discloses the direct-use warning about URL provenance. This fully discloses behavior beyond what annotations offer.

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 description is well-structured and front-loaded with the core action and return value. The second paragraph is a crucial warning about URL usage, which, while verbose, directly prevents the most common failure. No sentence is redundant; it is detailed but appropriately organized for the complexity.

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?

For a tool with 3 parameters and no output schema, this description is exceptionally complete. It explains the return value (file id and usage in templates), parameter behaviors (variants, transcoding), constraints (size, formats, SSRF), failure handling (404 guidance), and provides practical usage guidance. Nothing an agent needs to call it correctly is missing.

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 baseline is 3. The description adds meaningful semantics beyond schema: for 'url' it specifies public HTTP(S), size limit, and SSRF refusal; for 'purpose' it explains that variants are generated and transcoding occurs. 'templateId' is succinctly described as scoping for organization. While not exhaustive for every edge case, it substantially enhances parameter understanding.

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 states a specific verb ('Fetch', 'validate', 'store'), names the resource ('public image URL', 'Walletap-managed storage'), and explains the return value (file id). It clearly distinguishes from sibling tools like get_file, delete_file, and list_templates by describing the unique upload-from-URL operation.

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 explicit guidance on when to use the tool (when you have a user-provided or fetched URL) and clear exclusions: 'Do not construct a plausible-looking asset URL from a brand name' and 'if the fetch reports 404, find a different one rather than retrying'. This directly addresses common failure modes and instructs the agent on appropriate alternatives (ask the user), leaving no ambiguity about invocation.

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