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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds useful context by signaling that the tool surfaces interpretation caveats (missing-data rules, sample floor) rather than raw data, which helps distinguish it from data-retrieval siblings, but it says nothing about auth requirements, rate limits, or error behavior.

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 filler; every listed facet earns its place by telling the agent exactly what semantic guarantees it will receive back.

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 read-only metadata lookup with a defined output schema, the description covers what the result contains, and return formatting need not be explained. The only shortfall is that it never says when in a workflow to call it (e.g., before aggregating on a metric), which is a minor gap for a low-complexity 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 67%, and the schema itself documents the two meta-parameters (reason, user_intent) while exposing a 27-value enum for metric_id. The description adds no parameter-level detail at all, but the enum values are self-describing enough that the schema carries the load; this lands at the minimum-viable baseline rather than a compensation score.

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 ("Explain") and resource (a Flowlines metric's definition) and then enumerates exactly which facets are covered: denominator, time anchor, missing-data rules, precision, sample floor. No sibling tool (get_signal, get_map, list_*) performs this metadata-lookup role, so an agent can select it without ambiguity.

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 only implied: an agent infers it should call this when a metric's semantics are unclear before aggregating or comparing. There is no explicit "use this before calling aggregate_sessions" style guidance, no when-not-to-use, and no named alternative for retrieving metric values themselves.

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