feeds_ops

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

With no annotations, the description carries the full burden but only partially meets it: it discloses that the tool is stateful (vs single-shot fetch) and that responses follow a success/message/payload shape. It says nothing about the destructive semantics of unsubscribe/remove_item, permission or auth requirements, or rate limits on refresh_all.

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 purpose, then clearly sectioned into rationale, return format, and examples. The rationale section is somewhat self-referential meta-commentary, but overall the structure is tight and every example earns its place.

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?

An output schema exists, so the return-format section is arguably redundant, and the real gap is the undocumented parameters and unstated side effects for the mutating operations. For a 10-parameter, 13-operation mega-tool with zero annotations, the description is only minimally sufficient.

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 only 10% across 10 parameters, so the description is expected to compensate heavily. The examples clarify operation, url, limit, and unread_only, but feed_id, item_id, is_read, is_starred, opml_text, and title are left entirely undocumented in both schema and prose.

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 the resource (feed subscriptions) and enumerates the full operation set — subscribe/unsubscribe/list/refresh/fetch/get/mark/star/remove/opml/health — which tells an agent exactly what surface this tool covers. It does not, however, differentiate itself from the actual siblings (reader_ops, readability_ops); its only comparison is to 'glance-mcp,' which is not in the sibling list.

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?

The four examples imply usage for a handful of operations, and the rationale explains why the operations are consolidated into one tool. There is no explicit when-to-use / when-not-to-use guidance relative to reader_ops or readability_ops, so an agent must infer from the operation names alone.

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