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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=true. The description adds the useful behavioral constraint that it performs no model or chain RPC calls, but it does not describe the returned catalog structure or any limits, so the added transparency is modest.

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?

Two tightly written sentences with no filler, and the main purpose is front-loaded. The second sentence adds an important contrast without wasting space.

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 zero-parameter catalog tool with full annotation coverage, the description sufficiently explains the catalog's contents and its non-RPC nature. It could be stronger by explicitly tying the catalog to analytics_query, but it is complete enough for correct invocation.

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?

The tool has zero parameters, so parameter semantics are not a meaningful burden. The schema has 100% description coverage and the description correctly discusses only what the catalog contains, not parameter usage.

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 clear verb ('Discover') and lists specific resources: native metrics, semantics, aggregations, coverage requirements, and executable query examples. It distinguishes itself from an execution tool by being a catalog and by stating it makes no model or chain RPC calls, though it does not explicitly name the sibling analytics_query.

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 by 'Discover' and by the contrast with RPC calls, suggesting this is a reference/discovery step rather than query execution. However, it never explicitly says when to call this versus fet112.analytics_query or that it should be used before querying.

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