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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds valuable behavioral context beyond these: it discloses the fuzzy-match suggestion behavior on miss, and it describes the nature of the returned data (identity, raw signals, sub-scores, evidence-ready status). This is exactly the kind of context that helps an agent anticipate results. No contradiction.

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 concise sentences. It front-loads the purpose, then details the return contents, then gives crucial miss-handling guidance. Every sentence earns its place and there is no fluff or redundancy.

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?

The description covers the core purpose, the specific category scores, the return components, and the edge-case behavior when the handle is not found. The output schema exists and likely documents exact field structures, so the description need not repeat return format details. For a single-parameter read-only tool, this is complete and actionable.

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 a single parameter and 100% schema description coverage, the schema already thoroughly documents the 'handle' including format and examples. The description adds no additional parameter semantics beyond what the schema provides, so the baseline of 3 is appropriate.

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 uses a specific verb ('Get') and resource ('full details for a specific AI agent'), enumerates the included category scores (model_family, tokenized, service, developer), and lists specific return components (identity, raw signals, sub-scores, evidence-ready status). This clearly distinguishes it from sibling tools like get_agent_trust or get_agent_changes, which target narrower aspects.

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 gives clear context: use this tool to retrieve comprehensive agent details. It also provides an explicit behavioral instruction for not-found handles: 'LLMs should use these instead of hallucinating "agent doesn't exist"'. However, it does not explicitly name alternative sibling tools or state when to prefer one over another, so it misses the top tier for usage guidelines.

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