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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds genuinely new context: it writes flayr data under a `write` scope, the source image is not modified, and repeated identical inputs are free (cost/dedup behavior). It does not cover rate limits or failure modes. Note that 'same inputs again are free' is about billing, not identity, so it does not contradict idempotentHint=false.

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?

Front-loaded with the scope tag, then the core action and its output, then usage, then cost. Every sentence carries information and the trailing 'Wraps POST /api/v2/frames/apply' is a compact API pointer. Slightly dense bracket/parenthetical stacking keeps it from a 5.

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 12-parameter mutation tool with nested objects and no output schema, the description supplies the essentials an agent needs: what it produces (a URL), that the original is safe, how to consume the result, and that it is free. The remaining parameter semantics live in a reasonably documented schema, so the gaps are minor.

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 67%, with many parameters (frameRef, aspect, paletteOverride, contentId, platform) already documented inline. The description adds the contentId + platform pairing semantics, which is useful, but leaves fit, zoom, offsetX/Y, slideIndex and texts entirely to the schema. Baseline 3 is appropriate given the schema does most of the work.

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 names a specific verb and resource ('Draws a frame over an image') and states the concrete output ('returns a new image URL'). It also clarifies the non-mutating nature of the source ('the original is untouched'). However, it never explicitly distinguishes itself from the close siblings create_frame / get_frame / list_frames, so an agent must infer that those define or fetch frames while this one renders one.

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?

It gives two concrete downstream paths: 'Use the URL in create_content, or pass contentId + platform so that post publishes the framed image on that platform.' That is real when/how guidance tying the tool into a workflow. It stops short of exclusions (e.g., 'to define a reusable frame, use create_frame instead') or prerequisites, so it is clear context without alternatives.

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