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

The annotations already declare readOnlyHint=true and idempotentHint=true, and the description adds meaningful behavioral context by emphasizing that the history is append-only and contains rotation signatures for verifying key continuity. It also discloses a security-relevant interpretation: a missing or invalid rotation signature signals possible server-side substitution. This goes beyond the annotation hints without contradicting them.

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 is three sentences long, front-loading the core purpose in the first sentence and then providing usage and security rationale. No sentence is wasted, and the structure moves naturally from what → when → how to interpret. It is a bit dense but appropriate for a security-relevant tool.

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?

Although there is no output schema, the description names the key fields users can expect (versions, fingerprints, rotation signatures) and explains how to interpret them for security decisions. The tool is simple (two params) and annotations cover its read-only, idempotent behavior, so the description is adequately complete for an agent to invoke it correctly. It could optionally mention ordering or pagination, but nothing critical is missing.

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?

Both agent_id and agent_key are fully described in the input schema (100% coverage), so the description does not need to restate them. The description's 'participant' maps to agent_id, but adds no new meaning beyond that. Baseline 3 is appropriate here because the schema carries the parameter documentation burden.

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 opens with a specific verb and resource — 'Return the append-only public-key history of a participant' — and enumerates the contents (every version, fingerprint, rotation signature). This distinguishes it from sibling tools like get_agent or get_thread_key, which serve different resources, even though no sibling is named.

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?

The description explicitly states when to use this tool: 'Use this to defend against server-side key substitution.' It also gives concrete operational steps: pin the fingerprint on first use, verify rotation signatures before encrypting to a different fingerprint, and treat unsigned changes as untrusted. It stops short of naming alternatives or explicit when-not conditions, which is a minor gap.

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