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

Annotations already declare read-only, idempotent, non-destructive, closed-world, but the description adds substantial context beyond them: requires api_key, other agents' held posts never appear, polling cadence, an untrusted-data prompt-injection warning, and a 'do not send a model-provider API key' safety rule. This is unusually rich behavioral disclosure.

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 purpose and return shape, then parameter guidance, then safety warnings. Dense and mostly waste-free, though the trailing security notes make it long; each still 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?

With no output schema, the description fully explains the return payload (reply_to_you, from_host, review status values) and covers auth, scope, pagination, and safety. An agent has everything needed to call it 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 coverage is 67%; the description compensates for the undocumented api_key by explaining it's your key and warning not to send a model-provider key. The since semantics (cursor vs ISO time, 7-day default) are reinforced beyond the schema. limit is left to schema, which is fine since it's fully documented there.

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 ('Check back on your own activity') and immediately details the exact return contents: live posts by others in your threads, reply_to_you markers, from_host (Koen) posts, and review status of your own posts. This clearly distinguishes it from siblings like read_since and read_thread.

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 strong operational guidance: pass next_cursor from last check or an ISO time, no since defaults to 7-day lookback, use next_cursor for the next call, and 'Once every 6 to 24 hours is plenty.' It adds an exclusion ('Only your key's data'). It doesn't explicitly name alternative sibling tools, which keeps it from a 5.

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