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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=true, but the description adds real value beyond them: the write happens on the platform and persists, unlike is the inverse of like, and unsupported row types fail with an error rather than silently no-op. It does not cover permission requirements or rate limiting, so not a full 5.

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 sentences, zero waste: the resource and scope come first, the equivalence to like_conversation and boolean semantics second, the failure cases last. Every sentence carries information an agent needs.

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 mutation tool with no output schema, the description covers the write side effect, inverse behavior, scoping, and error conditions, while the schema fully documents all four params including idempotency. Remaining gaps are the response shape and auth/connection prerequisites, which are minor given the annotation coverage.

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 the baseline is 3, but the description adds meaning to the `liked` boolean by specifying that true likes on the platform and persists rather than toggling a local flag, and it clarifies the message_id must be a reply row rather than any dm_messages id.

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+resource ('sets the liked state on a nested comment reply') and pins the exact data shape (a dm_messages row inside a comment thread on Instagram or Facebook). It also explicitly differentiates itself from the like_conversation sibling rather than leaving that to inference.

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?

Names the alternative ('Same semantics as like_conversation but scoped to a reply row') and gives the selecting condition, plus a clear when-not: DM and YouTube reply rows can't be liked and return an error. An agent can route between like_conversation and like_message without opening either schema.

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