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

Annotations only declare it is a non-destructive write; the description adds the genuinely non-obvious behavior that an edit becomes a tap-to-confirm card unless the app holds publish rights. That is real context an agent cannot infer from the structured fields, though it omits what happens to the original text or whether the card expires.

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?

It is short and front-loads the core action, but the telegraphic fragments ("A card they tap unless this app may publish there") read as clipped shorthand that costs clarity. Compression here trades away readability rather than trimming waste.

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 three-parameter tool with full schema documentation and no output schema, the description covers the action, the approval flow, and sibling routing. Only minor gaps remain, such as what a successful edit returns or how drafts surface afterward.

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%, and the schema itself documents mode, text, and postId including the draft-vs-publish distinction, so the description adds no parameter meaning beyond it. The baseline of 3 applies.

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?

"Change a post's words" gives a specific verb+resource, and "on a channel they run" adds a scope constraint that narrows it meaningfully. It does not explicitly name create_post as the contrasting sibling, but the edit-versus-create distinction is unambiguous from the wording.

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?

"Only when they ask" is an explicit usage precondition, and "Delete and comments: more_tools" routes the agent away from this tool for adjacent operations. It stops short of a full when/when-not treatment (e.g., editing a draft vs a published post), but the key selection signals are present.

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