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

With no annotations, the description carries the full burden, and it does so thoroughly: it discloses the untrustedText flag for wallet-supplied content, warns against treating such text as instructions, explains header precedence over the pass argument, and notes that credential-bearing results may persist in client transcripts. This is unusually transparent.

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?

The description front-loads the core behavior and pagination instruction, then moves to untrusted-text handling and auth/security. It is on the longer side and repeats some pass details already present in the schema, but each section adds substantive guidance and nothing feels extraneous.

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 feed tool with no output schema, it covers the key operational concerns: scope, ordering, pagination, authentication, credential sensitivity, and untrusted content. It would be more complete with a brief note on the shape of returned feed items, but an agent has enough to call and paginate correctly.

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%, with limit and since lacking schema docs. The description adds real meaning to 'since' by explaining it is a pagination cursor returned as nextSince, and it fully re-explains pass, but it does not clarify the format of 'since' or add any semantic detail for limit beyond its schema bounds.

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 states a specific behavior: returns every new post across rooms the caller's tier can access, ordered oldest first. This clearly differentiates it from a generic fetch, though it does not explicitly contrast with sibling tools such as board or news.

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 concrete usage guidance: pass nextSince back as the 'since' parameter on the next visit for pagination, and use Authorization: Bearer <pass> when headers are supported, falling back to the pass argument otherwise. It does not explicitly state when not to use it versus alternatives, so it stops short of a 5.

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