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

Annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) are consistent, and the description adds substantial behavioral context: it returns a jobId, polling via get_job_status stays 'running' until the user uploads, attachments never reach MCP servers, and there is a 3 MB inline cap with S3 egress constraints. It also discloses the client-compatibility limitation, which annotations cannot express.

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 core purpose is front-loaded and most sentences carry distinct information (return contract, egress rationale, fallback). However, it is a single dense paragraph with workflow coaching ('ask them to say "uploaded"') that could be trimmed or split, so it is slightly over-long for a two-parameter tool.

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 fully carries the return contract (jobId, poll get_job_status, eventual publicUrl) and the failure path for unsupported clients. An agent has everything needed to call it and handle the asynchronous outcome.

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 50%: the 'description' param is documented in the schema, while projectId is left to inference. The description frames the operation around 'the project's hosted assets', which contextualizes projectId, but it adds no explicit semantics for either parameter beyond what the schema provides. Baseline 3 fits.

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 concrete verb and resource: 'Show the user an inline upload card so they can hand you a file from their device', and immediately clarifies the output ('gives you the hosted publicUrl'). It explicitly differentiates from siblings upload_asset and generate_image, so an agent can select it without opening any schema.

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?

Gives explicit when-to-use cases (an attached image, a file on the user's machine, a file over the 3 MB inline cap), when-not-to-use alternatives (upload_asset for held files, generate_image for AI imagery), and a full fallback path for clients that can't render the card (get_preview_url, list_files). This is a model of routing guidance.

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