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

Annotations cover safety (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description layers on non-obvious behavior the annotations cannot express: accepted formats, a 6 MB cap, server-side square cropping and 512 px resizing, and where the icon surfaces (chat header, emails, dashboard). That is exactly the extra context an agent needs before committing an upload.

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 dense paragraph that front-loads the verb, then the payload constraints, then the effect and permission requirement. Every clause carries information; no filler sentences.

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 not be described. Between the annotations (idempotent, non-destructive writes), the schema, and the description's format/size/processing/permission details, an agent has everything required to call this 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 coverage is 100%, so the baseline is 3, but the description goes beyond the schema's terse 'Base64 of the image file' by enumerating accepted formats (PNG, JPEG, WebP, GIF) and the 6 MB limit, plus guidance on the ideal source image. It adds real semantic value, though it doesn't discuss the app_id fallback beyond what the schema already states.

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 ('Uploads the app's icon') that is unmistakable and clearly distinct from siblings like set_android_push_key, set_ios_push_key, and update_app. The agent knows exactly what this does without inspecting the 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 a clear access precondition ('Owners only') and a recommended source ('the app's own 1024 px icon from the repository is ideal'), which tells the agent when invocation will succeed. It stops short of naming alternatives or saying when not to use this tool (e.g., versus update_app).

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