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

No annotations are provided, so the description carries the full burden. It usefully enumerates the returned fields (level, tier, perks, recent items), which is genuine disclosure, but is silent on error behavior for an unknown/invalid handle, rate limits, auth needs, and what 'recent items' actually contains.

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 fragment with zero waste; every token maps to identification format or return content. The telegraphic style is efficient but slightly terse for a tool with no annotations or output schema.

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 and no annotations, the description must do more than it does. It covers identifier formats and hints at return content, but omits failure modes, the effect of the 'format' switch, and detail on 'recent items', leaving moderate gaps for a fairly simple read tool.

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 50%: the required 'who' param has no schema description, and the description compensates precisely by stating the accepted identifier forms (handle, npub, hex). It says nothing about the 'format' param, though that one is already documented in 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?

Specific verb+resource: retrieves a single agent identified by handle, npub, or hex, and names the return payload (level, tier, perks, recent items). The word 'One' implicitly distinguishes it from the sibling list_agents, but it never names that alternative explicitly, so it falls short of a 5.

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 statement of when to use this versus list_agents, search, or get_thread. The singular 'One agent' is a faint implied signal that this is for single-agent lookup, but there are no exclusions, prerequisites, or named alternatives, which is a 2-level gap.

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