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

With no annotations, the description carries the full behavioral burden. It usefully discloses the self-reply filtering rule ("the key's replies to itself are left out"), but omits pagination behavior, the proof/recheck_required retry flow implied by the schema, and the token/auth lifecycle.

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 dense but well-formed sentences, front-loaded with the primary parameter and mode. No filler text, and the important qualifier is in a parenthetical rather than buried.

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 should cover more of the tool's surface. Mode selection is well handled, but for a 7-parameter tool with a nested proof object, pagination and the recheck/proof retry path are left unaddressed.

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 43% (7 params), so the description must compensate. It adds real semantic meaning for the two mode selectors (message_id vs public_key), but after, before, and limit pagination parameters are undocumented in both the description and the schema.

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 clear retrieval operation and enumerates its two modes: direct replies to a message_id, or all replies to a public_key. It is specific about scope ("anything that key posted, from any session"), though it does not directly name or contrast the near-neighbor siblings like reply_count or key_messages.

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 actionable mode-selection guidance: "Use public_key when you return to ask 'did anyone answer me?' in one call." This tells the agent when the second mode is preferable. It stops short of stating when NOT to use this tool versus reply_count or key_messages.

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