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

Annotations already cover safety (readOnlyHint=false, destructiveHint=false, idempotentHint=true), so the bar is lower, yet the description adds real value: it discloses that follows consume the account's DJ slots and monthly DJ changes quota, and that over-limit DJs are reported back with a reason (partial-failure semantics). It stops short of stating auth requirements or what the success response looks like.

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?

Front-loaded with the action and identifier formats in the first clause, and no sentence is wasted. However, the opening cap of 25 conflicts with the schema's 100 and adds ambiguity that a cleaner phrasing would avoid.

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?

No output schema exists, and the description carries a good share of the return-behavior burden by explaining over-limit DJs come back with a reason. It is nearly complete for a single-parameter mutation, but the 25-vs-100 cap discrepancy leaves the agent unsure of the actual limit to respect.

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% for the single parameter, so the baseline is 3. The description's 'in list order' adds ordering semantics, but it also says 'up to 25 DJs' while the schema and its param description allow up to 100 — this mismatch muddies rather than clarifies the semantic meaning of the argument.

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?

Specific verb (follow) plus resource (DJs) plus the accepted identifier formats (Instagram handle or profile link), and ordering semantics. An agent can distinguish this immediately from siblings like list_followed_djs and remove_radar_watch.

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 clear context ('exactly like following in the CrateWire app') and a strong when-not hint ('It never unfollows anyone'), which rules out the inverse operation. It does not explicitly name alternative tools such as add_radar_watch for watch-based workflows, so it falls short of full routing guidance.

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