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

Annotations already declare readOnlyHint=false, openWorldHint=true, destructiveHint=false, so the description's job is to add context, and it does: it discloses the output artifact type and dimensions, the auth scope required (write), and that the call is free of charge. It does not cover failure modes (private/deleted posts, rate limits) or how the returned media key is later consumed, which keeps it below a 5.

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 core action and output, followed by two short high-value sentences on cost and scope. The parenthetical field list is dense but efficiently conveys what the render contains. No filler sentences, though the phrasing is compressed to the point of being slightly cryptic ('media key').

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, yet the description still helpfully characterizes the returned artifact, and annotations carry the safety profile, so the remaining burden is small. The agent knows the input format (confirmed by schema), the theme/thread options, the cost, and the required scope. Only edge-case behavior for private or unavailable posts is unaddressed.

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 100%, so the baseline is 3. The description adds meaning for two parameters only ('dark or light' for theme, 'optionally under the post it replies to' for thread) and says nothing about variant or budgetUsd. It also asserts 'Free: nothing is charged' while a budgetUsd parameter with a $2 default and $10 cap exists, which is mildly confusing rather than contradictory.

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?

Specific verb (draw/capture) and specific resource (a public x.com post), plus the concrete rendered output (1080px-wide PNG media key with avatar, name, text, media, date, counts). This clearly separates it from generic page capture siblings like screenshot_page or record_page, though those siblings are never named. Purpose is unambiguous without opening 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?

Usage is implied rather than stated: you reach for this when you want a rendered X post card as an image asset. There is no explicit 'use this instead of screenshot_page when...' guidance despite several capture-adjacent siblings, and no when-not-to-use condition. The prerequisites ('Needs the write scope') are stated, which partially compensates.

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