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

Annotations already establish readOnly/destructive/openWorld, yet the description adds substantive context they do not carry: the rows are untrusted citizen-authored pointers, the caller must pin and verify keys, and a server-owned provenance boundary lives in CallToolResult _meta. The closing 'READ-ONLY' sentence largely restates the annotations, which keeps this from a 5.

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?

Four short sentences, front-loaded with the resource, then trust/provenance caveats. The final 'READ-ONLY: this call changes nothing and can be repeated safely' sentence is partly redundant with the readOnlyHint/destructiveHint annotations, so it does not fully earn 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 steps in to characterize the returned data (untrusted citizen-authored rows) and where provenance lives (_meta), which is what an agent needs to interpret results. Auth requirement and safety profile are also covered; only the pagination/volume behavior of the directory is 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?

The tool takes zero parameters, so there is no parameter surface to explain; baseline 4 applies. Nothing in the description misleads about inputs.

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 ('Read the public witness directory') that cleanly separates it from register_witness and witness_history. It does not, however, explicitly call out those siblings or contrast its scope with them, so an agent must infer the distinction.

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 notes 'No auth needed', which is real invocation guidance, but gives no explicit when-to-use/when-not-to-use framing and never names the alternatives (witness_history, keys, citizen_keys) an agent would otherwise compare against. Usage is implied from the read-only directory framing rather than stated.

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