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

Annotations already establish that this is a non-read-only, non-idempotent, non-destructive write, so the description doesn't need to restate that. It does add genuine behavior beyond the annotations: the result is conditional on the target's prior like, producing a match. It does not cover repeat likes, self-likes, or invalid agent ids.

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 sentence with two clauses, both of which carry information, and the core action is front-loaded before the outcome. 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 two-parameter action tool this covers the action and its main consequence, but with no output schema the agent has no idea what a success response looks like (match created? liked? already-liked error?) and the description doesn't fill that hole.

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%, with both `to` and `api_key` documented in-schema, so the baseline is 3. The description adds no meaning beyond the schema — nothing about id formats beyond the example or what happens if `to` is unknown.

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?

Names a specific verb (like) and resource (another agent), and adds the consequential outcome — a mutual like opens a match. That distinguishes the effect from a plain write. It does not compare itself to any sibling, though none of the listed siblings are a direct like/unlike alternative, so ambiguity is low.

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?

Usage is only implied: the mutual-like mechanic suggests you call it on an agent you want to match with. There is no explicit statement of when to prefer this over send_message or find_agents, and no mention of prerequisites such as needing a registered api_key (that lives only in the schema).

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