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

The description's 'Fetch' aligns consistently with readOnlyHint=true and destructiveHint=false annotations — no contradiction. But it adds nothing beyond the annotations: no details about return format, data freshness, or whether the intent is live-looked-up versus cached. With annotations already carrying the safety profile, the description contributes minimal incremental behavioral context.

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?

A single, front-loaded sentence with zero waste. The verb, resource, and access path appear in the correct order with no redundant qualifiers — the model of efficient description writing.

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 single-intent read with readOnly annotations and one required parameter, the essentials are present. However, in the context of nearly identical sibling tools, the lack of clarity on what 'ProtocolViewer' means as a distinct access path leaves an agent guessing at selection criteria. A sentence explaining the ProtocolViewer distinction would complete it.

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 100%, so the schema already documents intentHash and params. The description adds no meaning beyond what the schema provides — it doesn't clarify intentHash format (hex, encoded) or what the optional params object is for. Baseline 3 applies because the schema carries the load and the description adds nothing extra.

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 (Fetch), resource (single intent), and access path (directly from ProtocolViewer). Clear purpose, but sibling differentiation is weak: with ~100 siblings including peer_intent_show, peer_indexer_intents_show, and peer_pv_intent_list_owner, the description doesn't explain what distinguishes a ProtocolViewer fetch from these alternatives.

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?

No guidance on when to use this tool versus alternatives. The phrase 'directly from ProtocolViewer' hints at a specific access path but never states when this is preferred over peer_intent_show or peer_indexer_intents_show, nor when it should be avoided. Given the dense sibling family, this is a significant gap.

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