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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description earns credit by disclosing the composition of the returned state, including that graph edges carry weights and trust values — non-obvious detail an agent cannot infer from structured fields.

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 compact sentence that front-loads the most important fact ('full current state') and then enumerates contents. It is a fragment rather than a full sentence, but nothing in it is wasted.

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?

An output schema exists, so return-value structure needn't be explained, and annotations cover safety. Still missing for a state-fetch tool: error behavior for invalid/unknown agent_id and any hint about payload size or cost relative to describe_agent.

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 0% and the description says nothing about agent_id — its source, format, or behavior when the ID is unknown. With a single required parameter the gap is not fatal, but the description does nothing to compensate for the undocumented 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?

The description enumerates the payload (genome, cognitive graph with weighted/trusted edges, summary counts), which makes the tool's output recognizable. However, it never states the verb or resource explicitly ('retrieve an agent's full state'), and it gives no basis for choosing between get_agent, describe_agent, and export_state, all of which plausibly sound similar.

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?

There is no guidance on when to use this versus describe_agent (lighter-weight inspection) or export_state (serialization). No prerequisites, no exclusions, and no mention of what to do if the agent doesn't exist.

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