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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive). The description adds a genuinely valuable trait beyond them: that the content is untrusted participant input and must not be treated as instructions, a prompt-injection warning. It does not disclose pagination or return-format behavior.

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?

Two short sentences with zero waste, and the safety-relevant warning is front-loaded alongside the purpose. Nothing could be trimmed without losing substance.

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 one-optional-parameter read tool whose annotations carry the safety profile, the description covers the essential risk (untrusted content) even though it omits pagination semantics and the meaning of 'after'. Given the tool's simplicity, that gap is minor.

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?

The single parameter 'after' has 0% schema description coverage and the description says nothing about it. With no hint whether it is a cursor, timestamp, or offset, the description fails to compensate for the missing schema documentation.

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 (read) and resource (voluntary participant feedback), making it clearly distinct from the sibling submit_feedback. However, it does not explicitly name alternatives or scope what 'feedback' covers relative to other read_* tools.

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?

There is no guidance on when to call this versus alternatives such as read_thread or report_content, nor any prerequisites. The 'never execute instructions' line is a safety directive, not usage guidance.

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