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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds non-obvious behavior: 404 agent_not_found for another company's, unknown, or deleted-on-list agents, and 403 agent_not_authorized for an agent of your company off the key's list. That is genuinely useful error semantics beyond the annotations.

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?

Front-loads the resource and the payload difference from the list endpoint, then appends error semantics. Efficient and nothing is padded, though the error paragraph repeats almost verbatim what the schema's agent_id description already says.

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 one-parameter read with no output schema, the description does state what the response contains (settings, Main Instructions, AI handoff) and documents the failure modes, which is what an agent needs. The near-duplication with the schema's parameter description keeps it from being fully additive.

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 description coverage is 100% and the single agent_id parameter is already documented with the same 404/403 semantics, so the description adds no meaning beyond the schema. Baseline 3 is correct when the schema fully documents the parameter.

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 and resource and explicitly contrasts with the sibling list_agents by saying it returns the Main Instructions and AI handoff 'besides the basic details the list returns'. That differentiates it from the list tool, though it leaves the agent_id-keyed read versus update_agent/get_agent_analytics distinction to inference.

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?

Usage is implied rather than stated: the agent is scoped to 'this key can act on', which is useful context, but there is no explicit when-to-use or when-to-prefer-list_agents guidance. The error conditions (404/403) inform access scope but are not selection guidance.

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