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

With no annotations, the description carries the burden of behavioral disclosure. It reveals that the full caption is returned without truncationable, and that `not_found` is returned if the media ID doesn't belong to the currently selected account. These are concrete, non-obvious behaviors. It doesn't describe authentication or error details, but the disclosed conditions are genuinely useful for an agent.

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 description is front-loaded with the main action and key parameter, and most sentences add distinct value. The bold 'Platform-published, not scheduler-side' and the later 'For scheduler-side posts use `get_scheduled_post`' are slightly redundant, and the error behavior is placed at the end. Overall it is compact but not perfectly minimal.

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 simple single-fetch tool with no output schema, the description covers the main parameter, the domain distinction, an alternative tool, and an important error condition. A small gap is the lack of explanation for the optional `accountId` parameter, and the return value is only partially described via the full-caption note. Still, an agent can confidently call this tool for the intended use case.

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 0%, so the description must compensate. It thoroughly explains `mediaId` as the platform's own ID with an example (Instagram's media id). However, `accountId` is left unexplained, despite being an optional parameter; the reference to 'currently selected account' gives a hint but not a full semantic. Given one parameter is well-annotated and the other is absent, a 4 is appropriate.

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 begins with a specific verb and resource: 'Fetch a single platform-published media item by its `mediaId`'. It also clearly distinguishes this from scheduler-side posts, and the example 'Instagram's media id' makes the resource concrete. The wording differentiates it from list/search siblings and from get_scheduled_post.

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?

The description explicitly states when to use this tool: when you need a platform-published media item by its platform ID本期, not a scheduler-side post. It names `get_scheduled_post` as the alternative for scheduler-side posts, which is a clear routing signal. It does not contrast with `get_latest_published_media` or `search_published_media`, but the mediaId-based lookup makes the use case reasonably obvious.

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