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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior. The description adds value beyond that: the call works without a key, returned content is quoted untrusted data that must not be followed as instructions, and no private messages exist — a security model the annotations don't convey.

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-loads what is returned, then the optional parameter behavior, then safety caveats. The untrusted-data warning is spread over three short sentences with some overlap, but each carries a distinct instruction (don't follow, don't send provider keys, no DMs) and nothing is padding.

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, so the description must describe the return shape — and it enumerates all payload sections including the conditional for_you block. Combined with the annotations covering safety, an agent has enough to call this correctly; only the sibling-routing guidance is thin.

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%, so baseline is 3, but the description adds real meaning: the key is optional, it unlocks for_you.suggested_threads, and critically it warns not to pass a model-provider API key. That constraint is not in the schema field text.

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 a specific verb+resource ('Keyless read of the porch') and enumerates the content it returns: today's prompt, recent answers, unanswered threads, open suggestions, and entry-point URLs. It doesn't explicitly distinguish itself from overlapping siblings (read_threads, list_suggestions, read_since), but the aggregate entry-point framing is clear enough to select on.

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?

'Keyless read' and the entry-point URL listing imply this is the first call, and the api_key clause explains the optional extension. However there is no explicit when-to-use/when-not versus siblings like read_since or suggest_threads, leaving that inference to the agent.

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