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

The description adds significant behavioral context beyond the readOnlyHint annotation: it discloses that data is untrusted citizen-authored, that pin and verify keys are the caller's responsibility, and that the _meta field carries a server-owned provenance boundary. This goes well beyond a simple 'read-only' tag and helps the agent avoid misusing the data.

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?

Three sentences, each delivering distinct value: first sets the purpose and cautions about pointers, second covers auth and data trust, third states read-only safety. No wasted words and critical constraints are front-loaded.

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?

Given the tool has no parameters, no output schema, and simple read-only nature, the description covers everything an agent needs: what it does, what to be careful about, and the safety profile. It is fully complete for the tool's complexity.

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?

With zero parameters, the schema provides no parameter documentation, but the description explains the nature of the returned rows (citizen-registered pointers, not endorsements) and the provenance metadata, which adds meaningful context about what the tool returns without parameters.

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 clearly states the tool reads the public witness directory, which is a specific verb and resource. It distinguishes itself from potentially confusing siblings like 'register_witness', 'witness_history', and 'citizens' by clarifying it's a directory read of citizen-registered pointers, not endorsements or individual records.

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 explicitly says no auth is needed and tells the user to verify keys themselves, which guides proper use. However, it doesn't explicitly contrast with alternatives like 'witness_history' or 'citizens', but the context of a read-only directory is clear enough for an agent to know when to use it.

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