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

Annotations only declare the safety profile (not read-only, not idempotent, not destructive, closed-world); the description goes well beyond that by disclosing the polling cadence, the skip-existing-articles rule, the approval queue by default, the publish-scope requirement for autoPublish, and the exception where rule-breaking or credit-lacking posts still wait for approval. These are exactly the operational facts an agent needs before invoking a recurring automation.

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 tight sentences, front-loaded with the core action and the blog-address special case, then behavior, then constraints. Every clause carries information (skip rule, cadence, approval, TikTok exclusion, 10-feed cap) 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 mutation tool with no output schema, the description covers triggers, side effects, and limits thoroughly. The one gap is that it never says what the call returns (e.g. a feed identifier needed later by update_feed or unfollow_feed), which an agent managing the subscription lifecycle would benefit from knowing.

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 the schema already documents url, accounts, platforms, sourceUrl, and autoPublish in detail. The description adds only the nuance that autoPublish requires the publish scope and should only be set when the user asked — useful but largely duplicative of the schema text, so the baseline 3 applies.

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 (follows) plus resource (an RSS or Atom feed), with the extra scope that a bare blog address is accepted and its advertised feed resolved. It is immediately distinguishable from siblings like list_feeds, unfollow_feed, and update_feed, which manage existing subscriptions rather than create one.

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 operating context: today's articles are skipped, polling happens every 15 minutes, and autoPublish should only be used when the user explicitly asked. It also states two hard constraints (TikTok not a valid target, 10 feeds maximum). It does not, however, point to an alternative tool (e.g. schedule_post for one-off publishing), which is the only missing piece for a 5.

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