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

Annotations already flag a destructive, non-read-only, open-world write, and the description adds real context beyond them: the required `profile:write` scope, the fact that the first call mutates nothing, that unknown fields are refused by name, and that it returns a summary plus a confirm_token. That is a genuine behavioral contract for a destructive mutation.

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 action and the auth requirement, then the call sequence in short clauses; nothing is padding. The parenthetical about refused fields is slightly dense but earns its place by warning about argument validation.

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 two-parameter destructive tool with no output schema, the description covers permission, the confirm handshake, and dry-run behavior. It leaves open what the summary contains and what happens to the previous cover image, which are minor but noticeable gaps for a destructive write.

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 50%: confirm_token is described in the schema and the description adds useful sequencing (omit first, replay on second), but file_id is undocumented in both places — the agent gets no hint about where a file_id comes from (get_file, upload) or what it identifies. Baseline 3 fits given partial coverage and partial compensation.

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 first sentence names a specific verb and resource ('Set my cover image'), which is enough to separate it from set_avatar or update_profile by object. It stops short of explicitly contrasting itself with those siblings, so an agent must infer that cover image ≠ avatar.

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 gives concrete operating instructions: two calls, first call is a dry run that must be shown to the person, second call only after agreement with the confirm_token and the same arguments. What is missing is guidance on when to prefer this over the sibling set_avatar/update_profile paths, but the procedural when-to-use is unusually clear.

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