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

The description says "Liking twice keeps one like," which indicates idempotent behavior for repeated likes, but the annotations declare idempotentHint=false. This is a direct contradiction. Other behavioral context, such as the author seeing the like, is useful, but the idempotency mismatch is serious.

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 and appropriately short. The phrase "as the heart under a post does" is somewhat redundant and could be trimmed, but overall it is efficient.

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 two-parameter tool with full schema coverage and annotations, the description covers the core action and visibility. However, the idempotency contradiction means the behavioral picture is not fully reliable.

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 100%, so both post_id and unlike are already documented in the schema. The description reinforces the unlike behavior but adds no additional parameter syntax or constraints beyond what the schema provides.

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 states a specific verb and resource: like or unlike a Substack post as the authenticated user. It clearly distinguishes posts from sibling tools like like_comment by naming the resource directly.

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 explains how to remove a like via the unlike option and clarifies that the action is performed as the current user. It does not explicitly compare against like_comment or discuss when not to use this tool, but the usage context is clear.

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