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

Annotations already declare write-ness (readOnlyHint=false), idempotency, non-destructiveness and open-world behavior, so the safety profile is covered. The description adds the valuable dual-mode detail that the same call acts as an un-like when undo=true, but says nothing about the result of liking an already-liked post or auth requirements beyond what the schema notes.

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?

A single front-loaded sentence that states the action and the one non-obvious option, with no filler.

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, no-output-schema action tool the description is largely sufficient, especially with auth explained in the api_key schema field. The remaining gap — what a like returns or how repeat likes are handled — is minor.

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 only 33% — post_id and undo carry no schema text. The description compensates for the ambiguous one by explaining undo=true's meaning; post_id is self-evident as the target post, but no format or ID-source guidance is offered.

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 uses a specific verb and resource ('Likes a post') and explicitly covers the inverse operation via 'removes the like with undo=true', so an agent knows this single tool covers both like and unlike. No sibling competes for this action, so a dedicated differentiation clause isn't needed.

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 gives one concrete usage rule: pass undo=true to remove a like. It does not state prerequisites (sign-in or API key), nor when to prefer this over, say, comment or follow, so selection guidance is only partially implied.

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