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

Annotations only declare the generic safety profile (not read-only, not destructive, not idempotent); the description adds real semantics beyond them — partial update ('Only the fields given change'), no retroactive effect on existing posts, and the publish-scope requirement for autoPublish. It stops short of describing failure modes or the response, so it is strong but not exhaustive.

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 front-loaded sentences with zero filler: what changes, what is left alone, and which sibling to avoid. The parenthetical scope note is dense but earns its place by preventing an unauthorized autoPublish.

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 5-parameter mutation tool with full schema coverage and no output schema, the description covers purpose, partial-update behavior, side-effect scope, and alternative routing. Only minor operational details (e.g. behavior on invalid account ids) are absent, which the schema largely covers.

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 id, accounts, platforms, sourceUrl and autoPublish are already documented in the schema. The description reinforces accounts and autoPublish (including the publish-scope dependency) but adds no syntax or format detail beyond what the schema already provides; baseline 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?

States a specific verb (changes) and resource (a feed already followed) and names the exact fields affected: target accounts and autoPublish behavior. It is clearly separable from sibling follow_feed/unfollow_feed, which it explicitly contrasts itself against.

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?

Gives an explicit routing rule: 'Use it instead of unfollowing and following again, which would skip the articles already listed in the feed.' It also gates autoPublish with 'only when the user asked for it', so the agent knows both when to pick this tool and when to enable the risky option.

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