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

The annotations already declare readOnlyHint=true and destructiveHint=false, and the description correctly reinforces that opening the app writes nothing: 'nothing is saved until the user presses the button in the app.' It also discloses that the composer opens pre-filled and that publishAtUtc is rendered in the user's timezone, which are behavioral details not encoded in the schema or annotations. It stops short of saying what happens with an invalid postId or what the opened view returns, which keeps it off 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?

Three tight, front-loaded paragraphs: what the app is, when to call it, how draft behaves. The trailing Hungarian keyword line ('Magyarul: tartalomnaptár, Postemi megnyitása') is locale-matching boilerplate that isn't part of the tool's contract and slightly dilutes an otherwise efficient description.

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 an output schema present, the description needn't explain return values, and rich annotations cover the safety profile. All three params, including the nested draft object, are covered between schema and description, and the non-persistence caveat closes the one gap that could cause an agent to misreport that a post was scheduled.

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. The description adds a little framing around `draft` (pre-filled composer, unsaved until the button) and implies the view selector, but the individual params—view enum values, postId provenance, channelIds source—are all already documented in the schema, so there's limited added meaning.

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?

It states a specific verb plus resource ('Open the Postemi app in the chat') and enumerates the three surfaces the app exposes (calendar, composer, channels). It also explicitly distinguishes itself from the data-reading sibling list_posts, so an agent can route without opening either 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?

It gives explicit trigger conditions ('when the user asks to open Postemi, to see their content calendar, or to finish a post themselves') and an explicit alternative with the condition that selects it ('To answer a question about posts in words, use list_posts instead'). The draft path is also called out as the way to hand a written post over to the user.

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